© 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. 134315
    Prev
    Next
    INDEX
    Explanations

    defending hospitals

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

    function or matter

    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
     산업
    0.48
    vaart
    0.47
     공격
    0.46
     노
    0.46
     开发
    0.46
     econometric
    0.46
    有效的
    0.45
    음
    0.45
    客户端
    0.45
     空
    0.44
    POSITIVE LOGITS
    MAX
    0.42
    MoO
    0.42
    チャン
    0.42
    тите
    0.41
    ин
    0.40
    )((
    0.40
    無限
    0.40
     tasso
    0.40
     sque
    0.39
    シオ
    0.39
    Activations Density 0.000%

    No Known Activations