© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115219
    Prev
    Next
    INDEX
    Explanations

    awards, scholarships, and countries

    np_acts-logits-general · gemini-2.5-flash-lite

    AI service optimization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    た
    0.49
    сэн
    0.49
    skl
    0.48
     విలువ
    0.47
    चंद्र
    0.46
    RootDir
    0.46
     выбо
    0.46
    च
    0.46
    徝
    0.46
    はじめ
    0.45
    POSITIVE LOGITS
     junkie
    0.64
     Thailand
    0.54
     Albania
    0.52
     Italy
    0.52
     amaç
    0.49
     cruise
    0.49
     teria
    0.47
     Turkey
    0.47
    final
    0.47
    a
    0.47
    Activations Density 0.001%

    No Known Activations