© 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. 16-GEMMASCOPE-2-RES-262K
    7. 137783
    Prev
    Next
    INDEX
    Explanations

    names and code keywords

    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
    ,
    0.83
    ers
    0.68
    aj
    0.59
    il
    0.59
    allar
    0.59
     (
    0.58
    ala
    0.57
    esa
    0.57
    on
    0.57
    G
    0.57
    POSITIVE LOGITS
    ي
    0.89
    ة
    0.83
    و
    0.69
    会
    0.68
    ی
    0.66
    菂
    0.64
    色列
    0.62
    锜
    0.62
    邗
    0.62
    执行
    0.59
    Activations Density 0.000%

    No Known Activations