© 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. 10-GEMMASCOPE-RES-131K
    7. 21608
    Prev
    Next
    INDEX
    Explanations

    game starts

    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
    ارتمان
    -1.60
     représentent
    -1.47
    太大
    -1.47
    到
    -1.43
    ちょ
    -1.43
     empezaron
    -1.38
    unki
    -1.38
    返
    -1.37
     directrice
    -1.36
    imantan
    -1.35
    POSITIVE LOGITS
     in
    1.48
    in
    1.48
     for
    1.45
     of
    1.38
    ?”
    1.35
    溷
    1.31
     intended
    1.30
     â
    1.30
    情况下
    1.29
     like
    1.26
    Activations Density 0.023%

    No Known Activations