© 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. 115947
    Prev
    Next
    INDEX
    Explanations

    visual arts concepts and factual reporting

    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
    ziz
    -0.83
    レスト
    -0.82
     artistes
    -0.82
     beschikbaar
    -0.79
     Arturo
    -0.77
    RAE
    -0.77
    jei
    -0.76
    oplayer
    -0.75
    NTSTATUS
    -0.73
    Điện
    -0.73
    POSITIVE LOGITS
     figures
    0.99
     narrative
    0.93
     Academic
    0.92
    figures
    0.91
     monumental
    0.86
     figure
    0.83
     composition
    0.82
     Composition
    0.81
     modelling
    0.81
     fig
    0.80
    Activations Density 0.020%

    No Known Activations