© 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. 163354
    Prev
    Next
    INDEX
    Explanations

    incidents or injuries

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

    medical injuries and traumas

    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
    炀
    0.40
    Aligned
    0.39
    +)
    0.38
     للف
    0.38
    growth
    0.38
    !/"
    0.38
    ArchiveAction
    0.38
    www
    0.37
    颍
    0.37
    Growth
    0.37
    POSITIVE LOGITS
     alkoh
    0.54
     ölüm
    0.52
     sofern
    0.50
     medicamentos
    0.49
    injured
    0.49
     injure
    0.49
     tuj
    0.48
     cervical
    0.47
     julio
    0.47
     incid
    0.47
    Activations Density 0.000%

    No Known Activations