© 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. 245796
    Prev
    Next
    INDEX
    Explanations

    free Gems

    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
     Процитовано
    0.47
    Object
    0.46
    (()
    0.44
    Merhaba
    0.44
    Вот
    0.43
    ⤒
    0.43
    СП
    0.42
    Klik
    0.42
    Та
    0.42
    Теперь
    0.42
    POSITIVE LOGITS
    ایی
    0.50
     जला
    0.44
     awọn
    0.43
    队的
    0.43
    队
    0.43
     hóa
    0.43
    屌
    0.42
     ডিভিশ
    0.41
     দলে
    0.41
     উন্নতি
    0.41
    Activations Density 0.003%

    No Known Activations