© 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. 32855
    Prev
    Next
    INDEX
    Explanations

    Q:

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

    The neuron is triggered by code‐style identifiers or method/function names (long camelCase or technical tokens).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     réus
    -1.06
    uttered
    -0.98
    aktifkan
    -0.96
     Formule
    -0.94
     silnika
    -0.94
    +="
    -0.94
    otonic
    -0.94
     pasajeros
    -0.93
    champ
    -0.92
    JLabel
    -0.91
    POSITIVE LOGITS
     if
    0.98
     кроме
    0.92
    Torn
    0.90
     collaborator
    0.83
     by
    0.81
     scegliere
    0.81
     Среди
    0.80
     attivo
    0.80
    ས།
    0.79
     воспользова
    0.77
    Activations Density 0.000%

    No Known Activations