© 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. 34463
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     asfalto
    -1.37
    𓄹
    -1.33
    providedIn
    -1.30
     }));
    -1.27
    wijl
    -1.25
     trimestre
    -1.24
    bản
    -1.23
     diras
    -1.23
    　　「
    -1.23
    **/
    -1.23
    POSITIVE LOGITS
    '
    1.39
     gigantic
    1.37
    ,
    1.35
    A
    1.32
    D
    1.28
     '
    1.27
    I
    1.27
     AMAZING
    1.27
     alcune
    1.26
     ___________
    1.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.