© 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. 39392
    Prev
    Next
    INDEX
    Explanations

    luxury bath, Limited Company, William Eggleston

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

    character builder scaling

    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
    hdr
    0.50
    ľ
    0.48
    falling
    0.47
    rj
    0.46
     strolling
    0.46
    loc
    0.46
    無
    0.45
    j
    0.45
     obeying
    0.44
    r
    0.44
    POSITIVE LOGITS
     молока
    0.50
     eukary
    0.49
     Specify
    0.48
     Узбеки
    0.46
     ପ୍ର
    0.45
    TrackAngle
    0.45
     buildFor
    0.45
     Держа
    0.44
     мод
    0.43
     식으로
    0.43
    Activations Density 0.000%

    No Known Activations