© 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. 41-GEMMASCOPE-2-RES-262K
    7. 100020
    Prev
    Next
    INDEX
    Explanations

    formal / legal language endings

    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
     kraju
    0.46
    椑
    0.45
    കളെ
    0.42
    了这个
    0.40
     ท
    0.40
    കേ
    0.40
    𝖾
    0.40
    ayal
    0.40
    ফেট
    0.40
    popupBackground
    0.40
    POSITIVE LOGITS
    zelf
    0.47
     in
    0.45
     mesmas
    0.38
    ，
    0.38
     are
    0.37
     satisf
    0.36
    abouts
    0.35
     mesmos
    0.35
    jenigen
    0.34
     vesting
    0.34
    Activations Density 0.000%

    No Known Activations