© 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. 99841
    Prev
    Next
    INDEX
    Explanations

    companies, directors, portfolios

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

    web storage and gui elements

    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
    ៥
    0.57
     wouldn
    0.56
    volving
    0.54
    s
    0.54
    shire
    0.53
    ৪৩
    0.52
    XI
    0.52
    sinya
    0.51
     cenderung
    0.51
     hadn
    0.50
    POSITIVE LOGITS
    тику
    0.49
     د
    0.46
    utica
    0.45
    淘
    0.42
    تي
    0.42
    上
    0.42
    уд
    0.40
    使用
    0.40
    作物
    0.40
    اد
    0.39
    Activations Density 0.001%

    No Known Activations