© 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. 13504
    Prev
    Next
    INDEX
    Explanations

    payoff after what

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

    space wars, conscious creativity, focused learning

    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
     ditulis
    0.57
    스의
    0.50
    дил
    0.50
    oconvex
    0.46
    绡
    0.45
     karakteristik
    0.45
     Shabd
    0.43
     식으로
    0.42
     scanty
    0.42
    ორცი
    0.42
    POSITIVE LOGITS
    富
    0.50
    亲
    0.44
    विर
    0.42
    麵
    0.42
    後
    0.41
     大人
    0.40
    親
    0.40
     ідэ
    0.40
     天
    0.39
    台
    0.39
    Activations Density 0.000%

    No Known Activations