© 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. 26409
    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
     TÉ
    -1.12
    JAY
    -1.07
    用に
    -1.07
    cestry
    -1.06
     ENTERTAINMENT
    -1.02
     bym
    -1.02
     jú
    -1.00
     CHAIR
    -1.00
    anmar
    -1.00
     bús
    -1.00
    POSITIVE LOGITS
     also
    1.20
     of
    1.03
    min
    1.02
    k
    1.00
     Многие
    0.98
     B
    0.98
    te
    0.96
     T
    0.94
    l
    0.94
    ti
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.