© 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. 10849
    Prev
    Next
    INDEX
    Explanations

    time periods

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

    time units

    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
    $
    0.42
    LessThan
    0.41
    <strong>
    0.40
    <0x0D>
    0.40
    begin
    0.40
    待遇
    0.40
    日起
    0.39
    \
    0.39
    １
    0.38
    #
    0.38
    POSITIVE LOGITS
     профессор
    0.51
     toilette
    0.45
     provoquer
    0.43
     المع
    0.42
    elun
    0.42
    𝒊
    0.41
    㕕
    0.41
     coûte
    0.41
    BtnFill
    0.41
     вызыва
    0.41
    Activations Density 0.001%

    No Known Activations