© 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. 3871
    Prev
    Next
    INDEX
    Explanations

    health, safety, and social categories

    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
     bijective
    0.28
     vanilla
    0.26
    癹
    0.26
     bei
    0.26
    กับ
    0.26
     sinned
    0.26
    های
    0.25
     phenomenal
    0.25
    க்கொண்டு
    0.25
     in
    0.25
    POSITIVE LOGITS
     метою
    0.27
     書い
    0.25
     &/
    0.24
    -
    0.24
    -/
    0.23
    VOA
    0.23
    ↵↵
    0.22
     लाह
    0.22
     гром
    0.22
     пора
    0.22
    Activations Density 1.623%

    No Known Activations