© 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. 158405
    Prev
    Next
    INDEX
    Explanations

    setting, style, and beginning

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

    conclusion from

    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
    传播
    0.45
    propagation
    0.43
    စွာ
    0.43
    wet
    0.42
     encargado
    0.41
     splashed
    0.41
    诊
    0.41
    했으며
    0.41
     diffusion
    0.40
    可以是
    0.40
    POSITIVE LOGITS
     изменя
    0.53
     стиль
    0.50
     gestaltet
    0.50
     terdiri
    0.48
    ร
    0.48
     comienza
    0.47
     antiguo
    0.47
     від
    0.46
     سلسلے
    0.46
     comienzo
    0.46
    Activations Density 0.000%

    No Known Activations