© 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. 15962
    Prev
    Next
    INDEX
    Explanations

    and/or construction

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

    and/or and related concepts

    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
    ，
    0.69
    О
    0.61
    $,
    0.59
     Сасик
    0.54
    ،
    0.54
    Хо
    0.52
    Không
    0.52
    鷸
    0.52
    RULES
    0.51
    +,
    0.50
    POSITIVE LOGITS
     may
    0.67
     have
    0.62
    and
    0.59
     tyto
    0.58
    u
    0.57
     suas
    0.55
    ’
    0.54
     possui
    0.54
     provide
    0.54
     drew
    0.52
    Activations Density 0.013%

    No Known Activations