© 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. 10-GEMMASCOPE-RES-131K
    7. 22802
    Prev
    Next
    INDEX
    Explanations

    ages or durations

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

    The neuron activates on numeric tokens, i.e. numbers (including decimals and measurements).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Really
    -1.70
    celotti
    -1.66
     麵
    -1.66
     our
    -1.65
     internationaux
    -1.64
    How
    -1.63
     kobieta
    -1.61
     kobiety
    -1.61
    প্র
    -1.61
     データ
    -1.60
    POSITIVE LOGITS
    ogues
    2.03
    farer
    1.88
    rrrrr
    1.63
    >');
    1.63
    ❣
    1.63
    🤪
    1.62
    byes
    1.62
    nyard
    1.60
    </h1>
    1.59
    raisers
    1.56
    Activations Density 0.028%

    No Known Activations