© 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. 128231
    Prev
    Next
    INDEX
    Explanations

    code keywords and abbreviations

    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
    providedIn
    -2.70
     {}));
    -2.58
     IBOutlet
    -2.45
    但
    -2.39
     jTextField
    -2.38
     labyrinth
    -2.38
    ‪.‬‬
    -2.33
    涐
    -2.31
    珢
    -2.31
    衪
    -2.31
    POSITIVE LOGITS
     "
    2.81
     
    2.44
     mettent
    2.31
     abandonné
    2.31
     If
    2.30
    蹰
    2.25
    坶
    2.23
     decidedly
    2.14
     it
    2.11
     You
    2.09
    Activations Density 0.002%

    No Known Activations