© 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. 33414
    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
     for
    -1.41
    kenal
    -1.11
    imageio
    -1.06
     —
    -1.02
    вшие
    -1.01
    рующие
    -0.97
    CHRE
    -0.96
    зация
    -0.96
     who
    -0.96
     enige
    -0.96
    POSITIVE LOGITS
    を書いて
    1.18
    繊細
    1.13
     жк
    1.06
    ος
    1.04
     normalerweise
    1.03
    biendo
    1.02
    の味
    1.01
    錨
    1.01
     garder
    1.00
    Prova
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.