© 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. 41051
    Prev
    Next
    INDEX
    Explanations

    your ancestors

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

    adding ingredients or options

    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
     L
    0.57
    -
    0.56
     boring
    0.52
     de
    0.48
     D
    0.48
     es
    0.48
    ing
    0.48
     crazy
    0.47
    '
    0.47
     #
    0.46
    POSITIVE LOGITS
    glRaster
    0.63
    SScript
    0.56
    нди
    0.56
    rawData
    0.56
    pInBuffer
    0.55
    的处理
    0.55
    CommandBuffer
    0.54
     américains
    0.54
    tpVar
    0.54
    чиго
    0.54
    Activations Density 0.000%

    No Known Activations