© 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. 60631
    Prev
    Next
    INDEX
    Explanations

    languages and places

    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
    shuffle
    0.40
    spr
    0.39
    $$\
    0.38
    쟤
    0.37
    ad
    0.37
     cnt
    0.37
     Preg
    0.36
    밖에
    0.36
    ibo
    0.36
     aast
    0.36
    POSITIVE LOGITS
    redients
    0.43
    ค์
    0.40
    ीकृत
    0.40
     केन्द्र
    0.40
    ्ज
    0.39
    ్ఞ
    0.38
    बद्ध
    0.38
     INCLUDING
    0.38
    坯
    0.38
    مركز
    0.37
    Activations Density 0.002%

    No Known Activations