© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6275
    Prev
    Next
    INDEX
    Explanations

    asking "what is"

    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
    只想
    0.33
    ൃശ
    0.31
     তুলনায়
    0.31
    戕
    0.30
     위해
    0.29
     وړاندوینې
    0.28
     비교
    0.28
    の時間
    0.28
     상황
    0.28
     حصول
    0.28
    POSITIVE LOGITS
     is
    0.46
     happened
    0.45
    t
    0.43
     are
    0.40
    the
    0.39
     happens
    0.38
    chodzi
    0.38
    ts
    0.37
    to
    0.37
    `
    0.37
    Activations Density 0.215%

    No Known Activations