© 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. 193806
    Prev
    Next
    INDEX
    Explanations

    range of

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

    Discharge Machining

    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
     villes
    0.51
     cidades
    0.50
     GENERAL
    0.47
     وغيرها
    0.46
     Dé
    0.46
     "@
    0.46
     Yav
    0.46
     こちら
    0.45
     Предпо
    0.44
     turistas
    0.44
    POSITIVE LOGITS
    ფილი
    0.47
    Contain
    0.46
    allist
    0.46
    孜
    0.46
    잼
    0.45
    בודה
    0.44
    toprule
    0.44
    옴
    0.44
    ედ
    0.44
    挙げ
    0.43
    Activations Density 0.000%

    No Known Activations