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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87020
    Prev
    Next
    INDEX
    Explanations

    colors in themes

    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
     That
    -1.92
    </tr>
    -1.80
     also
    -1.71
     novidades
    -1.67
     certainly
    -1.64
    biendo
    -1.61
     categorized
    -1.57
     being
    -1.55
    ACIONAL
    -1.55
     {'
    -1.53
    POSITIVE LOGITS
    ↵
    1.98
    -
    1.90
    $
    1.85
     carrés
    1.68
    .
    1.66
    where
    1.63
    Compared
    1.63
    3
    1.59
    龊
    1.55
     اهم
    1.53
    Activations Density 0.002%

    No Known Activations