© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42839
    Prev
    Next
    INDEX
    Explanations

    what it means to

    np_acts-logits-general · gemini-2.5-flash-lite

    asking for meaning or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    på
    0.68
    pressure
    0.66
    in
    0.63
    inse
    0.63
    lir
    0.62
     extrême
    0.61
    b
    0.61
    ប្រភេទ
    0.60
    l
    0.60
    u
    0.60
    POSITIVE LOGITS
    意义
    0.70
    اری
    0.64
    这意味着
    0.64
     ramifications
    0.61
    ла
    0.59
    כה
    0.59
    оло
    0.58
     मतलब
    0.57
    었고
    0.56
     badge
    0.56
    Activations Density 0.027%

    No Known Activations