© 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. 22-GEMMASCOPE-RES-131K
    7. 127678
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric or quantitative tokens (e.g. digits, measurements, dosages, statistical values).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    given inside

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
    D
    -1.07
    <em>
    -1.05
     Like
    -1.03
     Remember
    -1.02
     Obviously
    -1.00
     to
    -0.99
     it
    -0.97
    Ḍ
    -0.97
     even
    -0.94
     obviously
    -0.94
    POSITIVE LOGITS
    Mvh
    1.06
    が変わ
    1.05
    LEIA
    1.03
    误会
    1.03
     rester
    1.03
    Spesifikasi
    1.03
    équilibre
    1.02
     necesarios
    1.02
     וק
    1.00
     descubrimiento
    0.99
    Activations Density 0.064%

    No Known Activations