© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14602
    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
     it
    -1.17
    botten
    -1.07
    今年
    -1.00
     while
    -0.98
    bø
    -0.97
    ATRE
    -0.96
    تاریخ
    -0.95
    کتاب
    -0.94
     can
    -0.94
     September
    -0.93
    POSITIVE LOGITS
    ごちそう
    1.41
     necesitaba
    1.34
     jsi
    1.33
    マジで
    1.33
    違和
    1.29
    −/−
    1.28
     equilíbrio
    1.27
    鮫
    1.25
    ほとん
    1.21
     perigo
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.