© 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. 31-GEMMASCOPE-2-RES-262K
    7. 110257
    Prev
    Next
    INDEX
    Explanations

    where tartar accumulates

    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_31_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
    angelo
    0.45
    greencar
    0.44
    \/}
    0.43
    is
    0.43
     welche
    0.43
     ಚಿ
    0.42
    PhysRev
    0.41
     القمر
    0.41
     jedna
    0.41
     procédure
    0.41
    POSITIVE LOGITS
    涨
    0.46
    激发
    0.45
    tements
    0.43
    在那里
    0.42
    রাত
    0.42
    其余
    0.41
    เรียก
    0.41
    投资
    0.40
    tg
    0.40
    语法
    0.40
    Activations Density 0.003%

    No Known Activations