© 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. 16-GEMMASCOPE-2-RES-262K
    7. 109751
    Prev
    Next
    INDEX
    Explanations

    Here we describe/report

    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_16_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
    IS
    0.59
    t
    0.56
    is
    0.54
    د
    0.52
    ش
    0.50
    ال
    0.49
    PH
    0.48
    in
    0.47
    reas
    0.47
    rof
    0.47
    POSITIVE LOGITS
    ።
    0.70
     они
    0.63
    เหล่านี้
    0.63
    𝚊
    0.60
    ный
    0.60
    ۔
    0.59
     Наталья
    0.58
    𒉰
    0.58
     К
    0.57
     По
    0.56
    Activations Density 0.013%

    No Known Activations