© 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. 125665
    Prev
    Next
    INDEX
    Explanations

    pick up

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

    picking and choosing

    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
     програм
    0.59
     contraception
    0.59
     от
    0.58
    парат
    0.55
     από
    0.54
     outil
    0.52
     ав
    0.51
     ク
    0.50
    จาก
    0.50
    처리
    0.50
    POSITIVE LOGITS
     밝혔
    0.47
    مش
    0.44
     المكان
    0.44
    تق
    0.43
    رح
    0.42
    بط
    0.42
    尤其是
    0.42
    chée
    0.42
    的主
    0.41
    chés
    0.41
    Activations Density 0.037%

    No Known Activations