© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87311
    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
     nuestros
    -1.04
     மற்ற
    -1.03
    pulseira
    -1.01
    DESCRIPCIÓN
    -0.98
    dáms
    -0.97
     décès
    -0.93
    BRID
    -0.92
    Steg
    -0.91
    Ubicación
    -0.91
    caneca
    -0.91
    POSITIVE LOGITS
     they
    1.30
    for
    1.08
    box
    1.02
    https
    1.01
    Tazama
    1.00
    base
    0.99
    かみ
    0.97
    r
    0.97
    technologies
    0.96
    titial
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.