© 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. 124713
    Prev
    Next
    INDEX
    Explanations

    other parties

    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
    guitarra
    -1.73
     of
    -1.63
     我们
    -1.51
     使っ
    -1.48
    </em>
    -1.48
     from
    -1.46
     our
    -1.43
    玙
    -1.43
    leyeb
    -1.43
    وازم
    -1.42
    POSITIVE LOGITS
    ’
    1.88
     beschreiben
    1.70
     feira
    1.70
     dispone
    1.67
    IFICATIONS
    1.66
    archical
    1.64
    ℟
    1.63
     devenu
    1.61
    метра
    1.59
    ℣
    1.59
    Activations Density 0.003%

    No Known Activations