© 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-65K
    7. 54700
    Prev
    Next
    INDEX
    Explanations

    introducing examples or clarifications

    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_65k_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
    W
    0.36
    ালন
    0.35
    ToSend
    0.35
     DISCLAIMED
    0.35
    H
    0.34
    K
    0.33
     ویکی‌پ
    0.33
    R
    0.33
    alen
    0.32
    N
    0.32
    POSITIVE LOGITS
    evším
    0.66
    прочем
    0.58
     aquellas
    0.54
    mittedly
    0.53
     übrigens
    0.52
     aquelas
    0.51
     अर्थात
    0.50
     aqueles
    0.50
     aquellos
    0.48
    此同时
    0.48
    Activations Density 0.088%

    No Known Activations