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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73723
    Prev
    Next
    INDEX
    Explanations

    appeal granted

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

    This neuron strongly activates on tokens that are numeric literals or identifiers containing digits (e.g. version numbers, class names with numbers, line counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     semper
    -0.74
    記述
    -0.72
     getSelected
    -0.68
    LIB
    -0.67
    开心
    -0.67
     Descriptors
    -0.66
    revalidate
    -0.65
    DESCRIPTOR
    -0.64
    чами
    -0.62
    filePath
    -0.61
    POSITIVE LOGITS
    lify
    0.69
     можли
    0.68
    🧺
    0.67
    bake
    0.66
     дека
    0.66
    study
    0.66
    udy
    0.66
     bake
    0.65
    ontrol
    0.65
    differ
    0.65
    Activations Density 0.076%

    No Known Activations