© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8117
    Prev
    Next
    INDEX
    Explanations

    U.K

    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
     when
    -2.77
     regarding
    -2.72
     there
    -2.69
     these
    -2.67
     doing
    -2.63
     should
    -2.59
    </h3>
    -2.56
     those
    -2.56
     on
    -2.50
     during
    -2.50
    POSITIVE LOGITS
     favoriser
    2.47
    椟
    2.36
     dismal
    2.33
     diminuer
    2.27
     générer
    2.23
     wist
    2.23
    毟
    2.23
    "
    2.17
    蟊
    2.17
    鲠
    2.13
    Activations Density 0.002%

    No Known Activations