© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8271
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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_31_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
     کی۔
    0.22
     فونبټ
    0.20
     tačiau
    0.20
     بالټ
    0.19
    \}.
    0.19
     ).
    0.19
     ولكن
    0.19
    荥
    0.18
     Tetapi
    0.18
     экран
    0.18
    POSITIVE LOGITS
     =
    0.42
    =
    0.39
     is
    0.29
     was
    0.28
    ="
    0.26
    =\
    0.25
    return
    0.25
    =(
    0.25
     :=
    0.25
     being
    0.25
    Activations Density 0.370%

    No Known Activations