© 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. 202592
    Prev
    Next
    INDEX
    Explanations

    instructions, notice, or requests

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

    rules, hotel, producers, Route, illness, messenger

    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
     संकट
    0.50
    .-
    0.48
     nurturing
    0.48
    .,
    0.48
    stackpath
    0.48
    ไง
    0.47
     stained
    0.46
    FileNotFound
    0.46
    ;
    0.46
     are
    0.46
    POSITIVE LOGITS
    zón
    0.51
    ベリー
    0.50
    ਚ
    0.50
    ί
    0.49
    ായിക
    0.49
    بية
    0.49
    삼
    0.48
    أي
    0.47
    ῎
    0.46
    nione
    0.46
    Activations Density 0.000%

    No Known Activations