© 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
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 57448
    Prev
    Next
    INDEX
    Explanations

    formulas and equations

    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_all/layer_41_width_262k_l0_big
    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
     두
    0.41
    不需要
    0.39
     hermit
    0.37
    لمانية
    0.35
    это
    0.35
     אחת
    0.35
     خانم
    0.35
     psychopath
    0.35
    ቶችን
    0.35
    ক্তার
    0.35
    POSITIVE LOGITS
    combined
    0.39
    )<<
    0.39
    )..
    0.38
    )”
    0.37
    )--
    0.37
    かつ
    0.37
    his
    0.37
    )">
    0.37
    POSTFIELDS
    0.37
    (&
    0.36
    Activations Density 0.004%

    No Known Activations