© 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. 128913
    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
    движи
    -1.25
    всем
    -1.24
    紫色
    -1.15
    母の
    -1.14
    uvres
    -1.12
     exceptionnel
    -1.09
     jagged
    -1.08
    Vaata
    -1.06
     mengucap
    -1.06
    guila
    -1.06
    POSITIVE LOGITS
     také
    1.08
    BorderSize
    0.99
     _________
    0.98
    ﺳ
    0.97
     certamente
    0.96
     heo
    0.95
     также
    0.94
    also
    0.92
     ___________
    0.91
    ovali
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.