© 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. 103957
    Prev
    Next
    INDEX
    Explanations

    disambiguation titles

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

    The neuron fires on numeric tokens—especially large numbers or section/page identifiers and similar numeric markers.

    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
    boven
    -0.88
    𝔥
    -0.73
     उपयोग
    -0.73
    ogeneous
    -0.72
    ường
    -0.71
    доби
    -0.70
    труд
    -0.69
    ಈ
    -0.68
    чу
    -0.68
     Game
    -0.68
    POSITIVE LOGITS
    perus
    0.90
    퐁
    0.85
     plains
    0.80
     punished
    0.78
     ){
    0.77
    壢
    0.76
     hô
    0.74
    EPS
    0.73
    acrylate
    0.73
     exemp
    0.73
    Activations Density 0.056%

    No Known Activations