© 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. 31-GEMMASCOPE-2-RES-262K
    7. 13902
    Prev
    Next
    INDEX
    Explanations

    signs and symptoms of medical conditions

    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_31_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
    👯
    0.46
    💼
    0.37
    ا۔
    0.36
    रोला
    0.36
    AdType
    0.35
    সুম
    0.35
    ুকু
    0.34
     ভাষার
    0.34
    Agregar
    0.34
    🥚
    0.34
    POSITIVE LOGITS
     severe
    0.52
     dangerously
    0.52
     instability
    0.50
     inefficient
    0.48
     acutely
    0.48
     distressed
    0.47
     unable
    0.45
     unstable
    0.45
     distress
    0.44
     severely
    0.44
    Activations Density 0.000%

    No Known Activations