© 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. 47144
    Prev
    Next
    INDEX
    Explanations

    copyright statements

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

    This neuron fires on numeric tokens—that is, digits or numeric literals embedded 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
     Handlung
    -0.89
     inapropiados
    -0.79
    tipos
    -0.75
    レコード
    -0.75
    本章完
    -0.74
    ,“
    -0.74
     summer
    -0.74
    ناك
    -0.73
    ungkinkan
    -0.73
     unfairly
    -0.73
    POSITIVE LOGITS
    hooks
    0.91
    '",
    0.91
     Nó
    0.84
    ük
    0.82
     Parcel
    0.81
     HOOK
    0.81
     cercando
    0.81
    imetric
    0.80
     morbidity
    0.80
    ietal
    0.79
    Activations Density 0.001%

    No Known Activations