© 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. 50428
    Prev
    Next
    INDEX
    Explanations

    my lucky stars

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

    specific token sequences

    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
    стоя
    0.49
    乐
    0.44
    ](#
    0.43
    时光
    0.43
    řit
    0.41
    coffee
    0.40
    zyc
    0.40
    伫
    0.40
    áv
    0.40
    нием
    0.39
    POSITIVE LOGITS
    ارتی
    0.46
     eponymous
    0.44
     앞에서
    0.44
    لول
    0.42
     엄마
    0.41
     nub
    0.41
    ן
    0.41
     কূটনীতিক
    0.41
     geophysical
    0.41
     সীমা
    0.41
    Activations Density 0.000%

    No Known Activations