© 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. 10-GEMMASCOPE-RES-131K
    7. 38697
    Prev
    Next
    INDEX
    Explanations

    map location or data

    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_10/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
    ");
    -1.52
    It
    -1.46
    This
    -1.46
    They
    -1.45
    ");
    -1.44
    ?”
    -1.43
    ;");
    -1.40
    </td>
    -1.38
    ")}
    -1.36
    foglal
    -1.35
    POSITIVE LOGITS
     it
    1.56
     будут
    1.48
     лучших
    1.46
     wisata
    1.37
    .'
    1.34
    two
    1.31
     mapa
    1.30
    ............
    1.30
     (...
    1.30
    APOR
    1.30
    Activations Density 0.009%

    No Known Activations