© 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. 76461
    Prev
    Next
    INDEX
    Explanations

    MINISTRY of, class

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

    website label configurations

    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
     जितनी
    0.46
    ूप
    0.44
    ளாவ
    0.44
     杯
    0.44
     ठंडा
    0.43
     Avocado
    0.43
     எதுவும்
    0.42
     शुद्ध
    0.42
     કુ
    0.42
     руба
    0.42
    POSITIVE LOGITS
    डीएम
    0.47
     vignettes
    0.47
    الم
    0.46
     آنها
    0.45
     préféré
    0.45
    ابقات
    0.45
     آنان
    0.44
    isance
    0.44
    ග
    0.44
    嘗
    0.44
    Activations Density 0.000%

    No Known Activations