© 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. 126126
    Prev
    Next
    INDEX
    Explanations

    latest data

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

    love to

    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
     enjeux
    0.43
    گیا
    0.43
     convene
    0.43
     hồn
    0.43
     reissue
    0.42
    ⚭
    0.42
     svojim
    0.41
    ໑
    0.40
    лат
    0.38
    เหน
    0.38
    POSITIVE LOGITS
    chessboard
    0.51
    tf
    0.50
    extractor
    0.49
    adapter
    0.47
     自転車
    0.47
    tar
    0.47
    toy
    0.46
     unpacking
    0.46
    tensorflow
    0.45
     Titanic
    0.45
    Activations Density 0.003%

    No Known Activations