© 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
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 69
    Prev
    Next
    INDEX
    Explanations

    python slicing and methods

    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_all/layer_41_width_262k_l0_big
    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
    .°
    0.61
    َان
    0.60
    indexBuffer
    0.59
     auffi
    0.58
    <unused1049>
    0.58
    ามารถ
    0.58
    routingHeader
    0.58
    荷重
    0.56
     quelquefois
    0.56
    OLYBD
    0.55
    POSITIVE LOGITS
    [:
    0.82
    [:]
    0.76
    startswith
    0.65
    in
    0.63
    [::-
    0.60
     __
    0.58
    __
    0.57
    [
    0.56
     pop
    0.55
    1
    0.54
    Activations Density 0.007%

    No Known Activations