© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 131057
    Prev
    Next
    INDEX
    Explanations

    storage partition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    在這裡
    0.42
    ሉት
    0.40
    UserState
    0.40
     мебель
    0.40
    📘
    0.40
    irit
    0.40
    ด้อ
    0.39
     권
    0.38
     ನೆಲ
    0.38
    өл
    0.38
    POSITIVE LOGITS
     Turbo
    0.40
     Bub
    0.40
    涡
    0.40
     Antalya
    0.39
     Turb
    0.38
     Turbine
    0.38
     Turk
    0.37
     Tor
    0.37
     Schl
    0.37
     Hel
    0.36
    Activations Density 0.021%

    No Known Activations