© 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. 130529
    Prev
    Next
    INDEX
    Explanations

    news and reporting contexts

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

    call, text, nursery, corporis, key

    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
    色
    0.48
     autént
    0.48
     кофе
    0.47
    දා
    0.45
    乸
    0.44
     çeşitli
    0.44
    డా
    0.44
     tanı
    0.43
     ऑक्साइड
    0.43
     empêcher
    0.43
    POSITIVE LOGITS
    u
    0.60
     resuspended
    0.48
    uploader
    0.48
    il
    0.48
    kook
    0.48
    it
    0.46
    uigen
    0.46
    rank
    0.45
    ㅠㅠ
    0.45
    宣告
    0.45
    Activations Density 0.000%

    No Known Activations