© 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. 16422
    Prev
    Next
    INDEX
    Explanations

    conjunctions and lists

    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
     etc
    0.72
    等
    0.68
     sebagainya
    0.67
    、
    0.66
    etc
    0.65
    等等
    0.63
    等の
    0.63
    或其他
    0.61
     тощо
    0.61
     whatnot
    0.60
    POSITIVE LOGITS
    和我
    0.44
    人和
    0.42
     跟
    0.40
    돠
    0.39
    지와
    0.39
    자와
    0.37
     與
    0.37
    时间和
    0.37
     እና
    0.36
    <unused2173>
    0.36
    Activations Density 0.118%

    No Known Activations