© 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. 161324
    Prev
    Next
    INDEX
    Explanations

    academic publication titles

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

    Sw Ave

    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
    那边
    0.43
    ┑
    0.41
    杰
    0.39
     metagen
    0.38
     chooser
    0.38
     βοη
    0.38
     facult
    0.38
    一对
    0.38
    ってきた
    0.37
    WP
    0.37
    POSITIVE LOGITS
    트는
    0.49
    дати
    0.45
    情報は
    0.45
    ridge
    0.43
     Gers
    0.43
    ⼈
    0.43
    stas
    0.42
    batross
    0.42
    𝗯
    0.42
     Tad
    0.42
    Activations Density 0.001%

    No Known Activations