© 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. 44635
    Prev
    Next
    INDEX
    Explanations

    headings, resources, and definitions

    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
    HTML
    0.44
     cron
    0.42
     inflammation
    0.41
    ipeline
    0.41
    }{
    0.40
     ure
    0.40
     marinated
    0.40
    型
    0.40
     filesystem
    0.40
     powdered
    0.40
    POSITIVE LOGITS
    Teacher
    0.42
    騏
    0.41
    Mobs
    0.41
     TimeSpan
    0.39
    Town
    0.39
     ओलंप
    0.38
    Chang
    0.38
     অভিভাবকদের
    0.38
     aunque
    0.38
     Chang
    0.38
    Activations Density 0.001%

    No Known Activations