© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118794
    Prev
    Next
    INDEX
    Explanations

    times and code comments

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

    This neuron activates on numeric tokens, i.e. digits or numbers (such as times, scores, measurements) in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ()+
    -0.82
    margins
    -0.80
    '};
    -0.80
    空调
    -0.74
    autoIncrement
    -0.73
     شام
    -0.71
    自分を
    -0.69
    anto
    -0.67
    alla
    -0.67
    jaardag
    -0.67
    POSITIVE LOGITS
    ziali
    0.81
     電動
    0.81
    стки
    0.80
     Playground
    0.79
     posteriorly
    0.77
    هنگ
    0.77
    NS
    0.77
    haustible
    0.76
    Кре
    0.75
    Открыть
    0.75
    Activations Density 0.006%

    No Known Activations