© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14194
    Prev
    Next
    INDEX
    Explanations

    function definitions and calls

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

    The neuron strongly activates on numeric literals (digits and numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     at
    -1.97
     for
    -1.91
     in
    -1.91
     as
    -1.77
     from
    -1.71
     because
    -1.68
     before
    -1.66
     without
    -1.66
     with
    -1.61
     spurred
    -1.61
    POSITIVE LOGITS
    –
    1.62
    部分を
    1.59
    儇
    1.56
    ፫
    1.55
     .......
    1.53
     ส์
    1.52
    nearly
    1.50
    ctory
    1.49
    andering
    1.47
    冖
    1.45
    Activations Density 0.009%

    No Known Activations