© 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. 14037
    Prev
    Next
    INDEX
    Explanations

    stating observations that

    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
    ，
    0.51
    ،
    0.51
    $,
    0.51
     point
    0.50
    __,
    0.48
     code
    0.47
     four
    0.45
     value
    0.44
     chain
    0.44
    <unused2113>
    0.44
    POSITIVE LOGITS
    Это
    0.60
    Đây
    0.59
    これが
    0.57
     ಇದು
    0.57
    ทีม
    0.56
    這是
    0.55
    สห
    0.55
     இது
    0.54
     הוא
    0.54
     זה
    0.52
    Activations Density 0.004%

    No Known Activations