© 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. 71986
    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
     शुर
    -2.30
    </sup>
    -2.22
     اما
    -2.20
    
    -2.17
    pernicus
    -2.17
     promoting
    -2.14
    ～♪
    -2.13
     to
    -2.11
     focusing
    -2.08
     cleverly
    -2.08
    POSITIVE LOGITS
     
    2.48
    偻
    2.38
    ments
    2.34
    ちょこ
    2.27
    くらいの
    2.22
    沵
    2.16
     prennent
    2.13
    or
    2.13
    could
    2.11
     _________
    2.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.