© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9433
    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
     stratég
    -1.20
    tų
    -1.16
     consultez
    -1.11
     sofá
    -1.11
     Wikipédia
    -1.09
     hjelpe
    -1.08
    ませんでした
    -1.05
    |$.
    -1.02
    為主
    -1.02
     tragé
    -1.02
    POSITIVE LOGITS
    alers
    1.13
    brtc
    1.08
     Allows
    1.05
    oczes
    1.02
     cinquième
    1.02
     जाए
    1.00
    注意到
    0.96
     quatrième
    0.96
    mators
    0.95
    chsel
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.