© 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. 136690
    Prev
    Next
    INDEX
    Explanations

    legal or consulting roles

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

    related to survival and specific persons

    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
     தெளி
    0.49
    )})
    0.48
     ಯಾವಾಗ
    0.47
     போட்ட
    0.46
     फाइन
    0.46
     सावधानी
    0.45
     λεπ
    0.45
     समायोजित
    0.43
     हमेशा
    0.43
     অপর
    0.43
    POSITIVE LOGITS
    ون
    0.47
    郗
    0.46
    Vista
    0.45
    吴
    0.45
    Plasma
    0.45
     époque
    0.44
    hock
    0.44
    但这
    0.44
    olids
    0.44
    鏻
    0.44
    Activations Density 0.001%

    No Known Activations