© 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. 125466
    Prev
    Next
    INDEX
    Explanations

    commands and work

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

    commit messages

    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
     worn
    0.49
    intendent
    0.43
     Giveen
    0.41
    شرات
    0.40
    瘠
    0.39
    uiden
    0.39
    今年的
    0.39
     ক্ষীণ
    0.39
     Strept
    0.38
    zentration
    0.38
    POSITIVE LOGITS
    ಡೆ
    0.43
     ETA
    0.42
    Work
    0.40
     Work
    0.40
    WB
    0.40
    lock
    0.38
    Ô
    0.38
    work
    0.38
    null
    0.38
    oreal
    0.38
    Activations Density 0.001%

    No Known Activations