© 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. 82552
    Prev
    Next
    INDEX
    Explanations

    searching by criteria

    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
     säga
    -1.13
     lägga
    -1.10
     môžete
    -0.95
    ٽ
    -0.92
    änderung
    -0.92
     hjälpa
    -0.92
    しまい
    -0.90
    Doktor
    -0.88
    ToAdd
    -0.88
    ходу
    -0.88
    POSITIVE LOGITS
     by
    5.06
    by
    2.16
    By
    2.03
    按
    1.98
     By
    1.94
     getBy
    1.88
     specific
    1.78
     based
    1.77
    ByName
    1.77
     по
    1.75
    Activations Density 0.024%

    No Known Activations