© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63373
    Prev
    Next
    INDEX
    Explanations

    counting length size count

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

    This neuron activates on numeric literals (digits) in code, identifying numbers such as counts, indices, and other numeric constants.

    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
     their
    -1.05
    vanni
    -0.93
    不仅
    -0.87
    崑
    -0.86
    licazione
    -0.85
    霈
    -0.84
    ۰
    -0.82
    🆆
    -0.81
    jawab
    -0.80
     perfeitamente
    -0.80
    POSITIVE LOGITS
    getCount
    0.97
     count
    0.97
     getCount
    0.96
     Count
    0.93
    Known
    0.91
     Counts
    0.87
    Count
    0.85
     COUNT
    0.85
    の数
    0.83
    ndez
    0.82
    Activations Density 0.004%

    No Known Activations