© 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. 21674
    Prev
    Next
    INDEX
    Explanations

    code context

    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
     enfermera
    -1.91
    戋
    -1.85
    mdash
    -1.85
    놋
    -1.80
    깽
    -1.78
     accesorio
    -1.75
     zrobić
    -1.74
    ⌵
    -1.73
    Daha
    -1.70
    鸩
    -1.70
    POSITIVE LOGITS
     of
    2.45
     from
    2.17
     with
    2.11
     also
    1.90
     it
    1.77
     There
    1.76
     on
    1.74
    </i>
    1.67
     at
    1.61
     επίσης
    1.57
    Activations Density 0.011%

    No Known Activations