© 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. 83922
    Prev
    Next
    INDEX
    Explanations

    people visit

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

    written by, kitty cat, surprisingly fruity

    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
    {\
    0.52
    ermont
    0.51
     .
    0.47
    ifts
    0.47
     Peterson
    0.47
     canyons
    0.47
     permissions
    0.46
    ที่คุณ
    0.46
     gulf
    0.45
     :
    0.44
    POSITIVE LOGITS
    䢔
    0.54
    ṗ
    0.50
     vienen
    0.48
    ሳ
    0.47
    setAutoDraw
    0.47
    Kelas
    0.46
     सीई
    0.45
    订
    0.44
    䚰
    0.44
     наш
    0.44
    Activations Density 0.001%

    No Known Activations