© 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. 8375
    Prev
    Next
    INDEX
    Explanations

    cognition and words following Wok

    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
    *
    -2.64
    ?
    -2.58
    ﹑
    -2.50
     —
    -2.38
    无疑
    -2.36
     carlo
    -2.28
    疍
    -2.25
    ⭏
    -2.23
     SEÑ
    -2.23
    {\
    -2.23
    POSITIVE LOGITS
     Provide
    2.73
     The
    2.50
    双方
    2.33
     blurred
    2.31
     Wonderful
    2.22
    
    2.22
    棺
    2.16
    
    2.16
     extremely
    2.11
     splendid
    2.11
    Activations Density 0.007%

    No Known Activations