© 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. 40-GEMMASCOPE-2-RES-262K
    7. 165974
    Prev
    Next
    INDEX
    Explanations

    personality, timeline, biographies, check

    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_40_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
    formats
    0.46
    posted
    0.42
    উ
    0.40
    ările
    0.40
    posts
    0.38
     بندی
    0.38
    ╩
    0.38
    拚
    0.38
     καθώς
    0.38
    頻道
    0.38
    POSITIVE LOGITS
     Schule
    0.37
    划
    0.36
     Blas
    0.36
    ولة
    0.35
     ضلع
    0.35
     Tis
    0.34
     glo
    0.34
    ')[
    0.34
     eeu
    0.34
    팜
    0.33
    Activations Density 0.000%

    No Known Activations