© 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. 34-GEMMASCOPE-RES-131K
    7. 103178
    Prev
    Next
    INDEX
    Explanations

    change color/facet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Handicapped
    -0.79
    ྨ
    -0.77
     messing
    -0.75
    rašymas
    -0.75
    않
    -0.73
     Conting
    -0.71
    ïse
    -0.71
     teamed
    -0.71
     Theaters
    -0.71
    Itr
    -0.70
    POSITIVE LOGITS
     chart
    0.96
     ；
    0.91
     seaborn
    0.88
    ageable
    0.85
    THS
    0.80
     rotated
    0.78
     grà
    0.78
     annot
    0.77
    տ
    0.77
    RoutingModule
    0.76
    Activations Density 0.005%

    No Known Activations