© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212192
    Prev
    Next
    INDEX
    Explanations

    bill of lading or election context

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

    Södermalm, judgments, Deadly

    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
     drawdown
    0.49
     Стаўкі
    0.48
    誘導
    0.48
    テナンス
    0.47
    儕
    0.47
    と考え
    0.46
    માન્ય
    0.46
    テーション
    0.46
     تیاری
    0.46
    ータ
    0.46
    POSITIVE LOGITS
    t
    0.51
     Feeling
    0.49
    risa
    0.48
    sc
    0.47
     (
    0.47
    whis
    0.46
     fiori
    0.46
     Clothing
    0.45
    Ranges
    0.45
    lanan
    0.45
    Activations Density 0.000%

    No Known Activations