© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 27323
    Prev
    Next
    INDEX
    Explanations

    traumatic brain injury

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    га
    0.67
    ли
    0.66
    ра
    0.62
     ಎಷ್ಟು
    0.61
    다라고
    0.60
    that
    0.60
    l
    0.59
    с
    0.59
    ev
    0.58
    angent
    0.57
    POSITIVE LOGITS
     quill
    0.57
    0.56
    વવા
    0.55
     appliqu
    0.55
    ,
    0.54
     sik
    0.54
     esprit
    0.54
     ago
    0.52
     axe
    0.52
     originals
    0.52
    Activations Density 0.001%

    No Known Activations