© 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. 76591
    Prev
    Next
    INDEX
    Explanations

    young boy, one

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

    monitoring AI compliance

    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
    Мы
    0.51
    뭡
    0.51
     Необходимо
    0.50
    Aqui
    0.50
    ApiKey
    0.49
     subalgebras
    0.48
    ጣል
    0.48
    息子
    0.48
    Чтобы
    0.47
    Sebagai
    0.47
    POSITIVE LOGITS
     le
    0.52
    ī
    0.48
     لار
    0.48
    ンテ
    0.48
    )}(\
    0.46
     Gone
    0.45
    ophyte
    0.44
    ERIAL
    0.44
    ع
    0.44
    ülő
    0.43
    Activations Density 0.001%

    No Known Activations