© 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. 1153
    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
     that
    -1.17
     雄
    -1.05
     adolescent
    -0.96
    库
    -0.95
     were
    -0.94
    ノ
    -0.91
     also
    -0.91
     didn
    -0.90
    trait
    -0.90
     Vaters
    -0.90
    POSITIVE LOGITS
     aña
    1.08
     perspective
    0.98
    راحی
    0.98
     línea
    0.94
     DEPOSITORY
    0.93
    
    0.93
     terceiro
    0.92
    shuff
    0.92
    λος
    0.91
    顰
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.