© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 1616
    Prev
    Next
    INDEX
    Explanations

    further north

    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
     quelquefois
    0.29
    َان
    0.28
    র্ষি
    0.27
    ンス
    0.27
    َة
    0.27
    َد
    0.27
    NESS
    0.26
    soluble
    0.26
    ratingBarStyle
    0.26
    IENCE
    0.25
    POSITIVE LOGITS
     of
    0.38
     to
    0.35
     out
    0.34
     up
    0.32
    적으로
    0.32
     on
    0.29
     from
    0.28
    听
    0.28
     apart
    0.27
    에서
    0.27
    Activations Density 0.001%

    No Known Activations