© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2479
    Prev
    Next
    INDEX
    Explanations

    device='cpu'

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is triggered by numeric tokens and hyphenated specification keywords (e.g. parameters, property names, and measurements) in technical‐spec text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical syntax elements in CSS and programming contexts, particularly property names, values, and delimiters.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    technical web graphics/layout terminology, especially CSS/SVG compositing, clipping, and hyphenated property names and operations

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputStream
    0.65
    Fcn
    0.62
    dataType
    0.62
    Compilation
    0.60
    PrintWriter
    0.59
    TypeId
    0.59
    Type
    0.59
    FRAGMENT
    0.59
    EDIA
    0.58
    Fragment
    0.57
    POSITIVE LOGITS
     ${({
    0.95
     none
    0.93
     unset
    0.91
     '';
    0.89
     auto
    0.83
     inherit
    0.82
     "";
    0.81
     rgba
    0.79
     calc
    0.77
     unapolog
    0.74
    Activations Density 0.019%

    No Known Activations