© 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. 10337
    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
     philosophie
    -0.98
     avocat
    -0.97
     taille
    -0.95
     сент
    -0.95
     hulle
    -0.95
     taux
    -0.90
    ”，
    -0.89
    庚
    -0.88
     هو
    -0.88
     épisode
    -0.88
    POSITIVE LOGITS
     acrescent
    0.96
    她就
    0.93
     WANTED
    0.93
     каких
    0.92
     größe
    0.92
     verkau
    0.91
    apprentissage
    0.91
     getrock
    0.90
    avenir
    0.90
     スポ
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.