© 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. 34-GEMMASCOPE-RES-131K
    7. 31882
    Prev
    Next
    INDEX
    Explanations

    code module or legal document

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

    The neuron activates on numeric tokens (e.g. line numbers, version numbers, or other integer literals).

    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
    collar
    -0.85
    nacht
    -0.81
     mukaan
    -0.78
    КТ
    -0.78
    dmg
    -0.76
    folds
    -0.76
    MeasureSpec
    -0.76
    komme
    -0.76
     lørdag
    -0.74
    cull
    -0.74
    POSITIVE LOGITS
     следует
    0.84
    貼り
    0.80
     herrera
    0.78
     rapids
    0.78
     ソー
    0.78
    ()=>{
    0.77
     poro
    0.76
    MSN
    0.75
     Noi
    0.75
    Gerhard
    0.75
    Activations Density 0.002%

    No Known Activations