Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 7204
    Prev
    Next
    INDEX
    Explanations

    powers of 2 and scientific notation

    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
    на
    0.79
    ール
    0.73
    ー
    0.65
     it
    0.64
    सं
    0.64
    它
    0.62
    സ്
    0.61
    лина
    0.59
    hedral
    0.58
    σσ
    0.58
    POSITIVE LOGITS
     стала
    0.78
     trailed
    0.73
    nál
    0.71
    ;
    0.71
    in
    0.70
    <0x80>
    0.68
     بيان
    0.67
     понадоби
    0.67
     caída
    0.66
    inan
    0.65
    Activations Density 0.038%

    No Known Activations