© 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. 11801
    Prev
    Next
    INDEX
    Explanations

    source code paths

    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
    tructive
    -0.94
    kursi
    -0.94
     対策
    -0.93
     opravdu
    -0.88
    persian
    -0.87
    ボーイ
    -0.87
     fhall
    -0.85
     feud
    -0.85
    ﾜ
    -0.84
    Več
    -0.84
    POSITIVE LOGITS
    main
    1.30
    ov
    1.17
     Whether
    1.00
    Whether
    0.99
    cher
    0.93
     principale
    0.93
     gt
    0.92
    ,.
    0.91
    ok
    0.90
     comedy
    0.88
    Activations Density 0.011%

    No Known Activations