© 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. 6472
    Prev
    Next
    INDEX
    Explanations

    bracketed citation numbers

    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
    粞
    0.39
    㫻
    0.38
    褛
    0.37
    螻
    0.36
    廛
    0.36
    <unused273>
    0.36
    垻
    0.36
    聑
    0.36
    ятся
    0.36
    пробу
    0.35
    POSITIVE LOGITS
     citation
    0.56
     Citation
    0.50
    ref
    0.49
    1
    0.49
     citations
    0.49
    reference
    0.48
     ref
    0.48
     reference
    0.47
     [
    0.46
    citation
    0.46
    Activations Density 0.003%

    No Known Activations