© 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. 5672
    Prev
    Next
    INDEX
    Explanations

    components and their paths

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

    The neuron flags technical UI‐related component names (e.g. “modal,” “Bootstrap’s,” “Image,” “Interface,” “section”).

    oai_token-act-pair · o4-miniTriggered 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
     props
    0.58
    ũ
    0.58
     controllers
    0.57
     çünkü
    0.57
     socket
    0.56
     devolution
    0.55
     routers
    0.55
     celebra
    0.55
     garlands
    0.55
     feminists
    0.55
    POSITIVE LOGITS
    Components
    0.69
    *;
    0.67
    ListComponent
    0.64
    เล็ก
    0.59
    Lifecycle
    0.59
    ;
    0.59
    _;
    0.57
     Components
    0.57
     ;$
    0.57
     _;
    0.56
    Activations Density 0.000%

    No Known Activations