© 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. 59316
    Prev
    Next
    INDEX
    Explanations

    case of

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

    origins and history

    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
    وم
    0.47
    permal
    0.45
    可以用
    0.45
    纵
    0.43
    在
    0.42
    一对
    0.41
    르는
    0.41
    дится
    0.41
    जै
    0.41
    aný
    0.40
    POSITIVE LOGITS
     своему
    0.50
     Örneğin
    0.49
     ছেলের
    0.49
    scored
    0.48
     ఘ
    0.46
    vorsch
    0.46
    EndPoint
    0.46
     오랜
    0.46
     прису
    0.46
     ஆகியோர்
    0.44
    Activations Density 0.000%

    No Known Activations