© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87052
    Prev
    Next
    INDEX
    Explanations

    school grade

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

    advice, criteria, or scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ط
    0.44
     bede
    0.43
     Lleg
    0.43
     strop
    0.43
     Ecusson
    0.42
     التي
    0.41
     brim
    0.40
    stripos
    0.40
     Tarifi
    0.40
     pric
    0.40
    POSITIVE LOGITS
    REG
    0.47
    ERS
    0.45
    🐖
    0.45
     аўтаматы
    0.44
    丷
    0.44
    レット
    0.43
    Jake
    0.43
    CTS
    0.42
    |
    0.42
    TIMESTAMP
    0.42
    Activations Density 0.000%

    No Known Activations