© 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. 83836
    Prev
    Next
    INDEX
    Explanations

    action level or vulnerability detection

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

    medical context and related terminology

    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
     ট্যাংক
    0.50
    اا
    0.49
    垁
    0.45
    лый
    0.44
    ripcion
    0.44
    用车
    0.44
    ﹰ
    0.44
    㐄
    0.44
     멋
    0.43
    霟
    0.43
    POSITIVE LOGITS
     vulnerability
    0.54
    /
    0.53
     medically
    0.52
     pathogenic
    0.52
     pertaining
    0.52
     detection
    0.50
     vulnerable
    0.50
     related
    0.50
     therefore
    0.49
     intensity
    0.49
    Activations Density 0.000%

    No Known Activations