© 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. 105570
    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
    鋨
    -1.05
    затор
    -1.02
     of
    -0.96
    ψε
    -0.94
     Heater
    -0.93
     bico
    -0.91
     However
    -0.90
     चुन
    -0.88
     Golfo
    -0.88
     crotch
    -0.87
    POSITIVE LOGITS
     вышел
    1.13
     saliendo
    1.08
     szükség
    1.04
     caminando
    1.01
    ridged
    0.99
     történ
    0.99
     escribiendo
    0.98
     jugando
    0.97
     Espagne
    0.96
    and
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.