© 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. 109646
    Prev
    Next
    INDEX
    Explanations

    calling 911

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

    reputational damage and societal impact

    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
    喚
    0.49
     увагу
    0.46
     Львів
    0.45
    غال
    0.45
     মনের
    0.45
     heating
    0.43
     hearings
    0.43
    ح
    0.42
    Hear
    0.41
     економі
    0.41
    POSITIVE LOGITS
    总结
    0.50
    ປະ
    0.49
    类似于
    0.47
    镇
    0.47
    مدينة
    0.46
    ്ട
    0.45
    ையே
    0.45
     desper
    0.45
     rep
    0.45
    代码
    0.44
    Activations Density 0.000%

    No Known Activations