© 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. 106405
    Prev
    Next
    INDEX
    Explanations

    events and news headlines

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

    The neuron is highly responsive to tokens that mark dates or time references (prepositions like “in,” “on,” “after,” numerals, month names), i.e. components of temporal expressions.

    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
     orthon
    -0.82
    piratory
    -0.80
    ábado
    -0.79
    ongono
    -0.78
    izando
    -0.76
    牀
    -0.76
     établie
    -0.76
    Zus
    -0.75
    vorous
    -0.75
     inlet
    -0.75
    POSITIVE LOGITS
     新品
    0.88
     Володи
    0.79
    entang
    0.76
    ẓ
    0.75
     Asi
    0.71
     lát
    0.71
     Fight
    0.69
    اير
    0.69
     Kost
    0.69
     Navy
    0.69
    Activations Density 0.003%

    No Known Activations