© 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. 10-GEMMASCOPE-RES-131K
    7. 22405
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     antigos
    -1.08
     incluyendo
    -1.05
     plantillas
    -0.98
    cadi
    -0.96
     こんな
    -0.96
     pequeños
    -0.96
    omalies
    -0.95
    湘南
    -0.93
     ingresos
    -0.92
     جديدة
    -0.92
    POSITIVE LOGITS
    aragus
    0.99
     altro
    0.97
    牁
    0.90
     fram
    0.90
    ungkan
    0.89
    Fußball
    0.88
     those
    0.88
    உ
    0.85
     quiz
    0.84
    joje
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.