© 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. 123354
    Prev
    Next
    INDEX
    Explanations

    fairly easy or niche

    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
     bibli
    0.52
     quadr
    0.48
     radi
    0.47
    ۔
    0.47
     libro
    0.46
     mö
    0.46
     bieden
    0.46
     paramet
    0.45
     konsult
    0.45
     bioge
    0.45
    POSITIVE LOGITS
    𝗣
    0.49
    Cancel
    0.47
     Expend
    0.47
    Successful
    0.46
     stripping
    0.46
    𝗧
    0.46
    تھی
    0.45
    Similarly
    0.44
    이
    0.44
    𝐏
    0.44
    Activations Density 0.002%

    No Known Activations