© 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. 41212
    Prev
    Next
    INDEX
    Explanations

    gb or gov followed by path

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

    candidate FYB202

    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
     сложных
    0.45
    你在
    0.45
    哥
    0.45
    硫酸
    0.44
    作品
    0.44
    生產
    0.44
    تك
    0.43
    当你
    0.43
    我们要
    0.42
     আত্মা
    0.42
    POSITIVE LOGITS
     Org
    0.49
     questionnaires
    0.47
     pertin
    0.47
    HEAP
    0.46
    리
    0.44
    ッグ
    0.43
    gesi
    0.43
     Reaktion
    0.43
     AO
    0.42
     NGS
    0.42
    Activations Density 0.000%

    No Known Activations