© 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. 22-GEMMASCOPE-RES-131K
    7. 15895
    Prev
    Next
    INDEX
    Explanations

    software license terms

    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_22/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
     on
    -2.55
     with
    -2.42
     from
    -2.17
     in
    -2.17
     their
    -1.98
     at
    -1.84
     by
    -1.83
     even
    -1.83
     using
    -1.73
     more
    -1.67
    POSITIVE LOGITS
    遊んで
    1.61
     développer
    1.59
     diversos
    1.58
    了一個
    1.56
    皷
    1.55
    你不要
    1.55
     potrebbe
    1.54
    嘮
    1.53
    蹩
    1.51
    楽しむ
    1.48
    Activations Density 0.055%

    No Known Activations