© 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. 33571
    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
    Fprintf
    -1.02
     desember
    -0.98
    чки
    -0.92
     Novembre
    -0.89
    lazione
    -0.89
    ोर्ट
    -0.89
    ofern
    -0.88
     oktober
    -0.88
     Dirección
    -0.88
    Website
    -0.87
    POSITIVE LOGITS
     comodidades
    1.01
     here
    0.95
    Ress
    0.94
    actividad
    0.92
     and
    0.91
     vendedores
    0.90
    alumni
    0.89
    jectile
    0.86
    donde
    0.85
    Garantie
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.