© 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. 44675
    Prev
    Next
    INDEX
    Explanations

    Chal- prefix

    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
     You
    -2.70
    啻
    -2.61
    that
    -2.55
     frantically
    -2.55
     neues
    -2.44
    襌
    -2.42
    と
    -2.34
    ︕
    -2.31
     insists
    -2.31
     knows
    -2.28
    POSITIVE LOGITS
    \
    2.78
    تیجه
    2.31
    ting
    2.31
    M
    2.30
     pleas
    2.30
    F
    2.25
    我们在
    2.23
    ༑
    2.19
    いぐるみ
    2.19
    棪
    2.16
    Activations Density 0.006%

    No Known Activations