© 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. 25669
    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
     Many
    -1.20
    licante
    -1.16
    Like
    -1.13
     skóra
    -1.12
     we
    -1.09
     it
    -1.09
     répon
    -1.07
    ocardial
    -1.03
     your
    -1.02
    Many
    -1.01
    POSITIVE LOGITS
    
    1.13
     graduación
    1.05
    Interes
    1.02
    upported
    1.01
    pecified
    0.99
    Vra
    0.98
    strual
    0.95
     بيها
    0.95
    氤
    0.94
    _{
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.