© 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. 245050
    Prev
    Next
    INDEX
    Explanations

    tasks, assignments, repayments

    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
     получает
    0.48
    ㄕ
    0.48
    剂量
    0.47
     ನಾಲ್
    0.46
     doğrud
    0.45
     формирование
    0.45
    勿
    0.45
    髄
    0.45
     сервера
    0.45
     충분
    0.45
    POSITIVE LOGITS
    Rio
    0.47
    RIO
    0.47
    id
    0.46
    ن
    0.46
    ub
    0.45
     somma
    0.45
    utia
    0.44
    ilization
    0.43
    ignal
    0.43
    inactive
    0.43
    Activations Density 0.000%

    No Known Activations