© 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. 25870
    Prev
    Next
    INDEX
    Explanations

    Ethernet Interface / programming context

    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
    INTRODUCTION
    0.50
    **
    0.48
    [
    0.48
    using
    0.48
    (
    0.48
     و
    0.45
    我
    0.45
    #
    0.45
    “
    0.45
    m
    0.44
    POSITIVE LOGITS
     αξ
    0.52
     컴퓨
    0.52
    겅
    0.51
     ສະ
    0.47
     ସ
    0.47
    𒁾
    0.47
    न्छ
    0.46
    ಸ್ಟ
    0.46
     半袖
    0.46
    挾
    0.46
    Activations Density 0.001%

    No Known Activations