© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74597
    Prev
    Next
    INDEX
    Explanations

    color orange

    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
    *
    -3.19
    を始め
    -2.56
    絎
    -2.53
     you
    -2.47
    鬭
    -2.42
    スポンサーリンク
    -2.30
     wichtigste
    -2.28
    をしています
    -2.23
     diseñ
    -2.22
    
    -2.20
    POSITIVE LOGITS
    攫
    2.63
    
    2.61
    徘
    2.31
    𓄹
    2.30
    ization
    2.27
    ции
    2.25
    合物
    2.20
    痢
    2.16
    遁
    2.14
     September
    2.13
    Activations Density 0.003%

    No Known Activations