© 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. 61923
    Prev
    Next
    INDEX
    Explanations

    aggregate particles, surgical technique, molecular weight, arrests, instructions, mother-daughter, nebulae, transistors, corruption

    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
    、、、
    0.42
     አይደለም
    0.42
    🎑
    0.41
    ꞎ
    0.40
    🥝
    0.39
    适用于
    0.38
    Unless
    0.38
     venen
    0.38
    聯盟
    0.38
    swürdig
    0.38
    POSITIVE LOGITS
    itt
    0.42
     mon
    0.41
     "{
    0.40
     Hell
    0.40
    font
    0.40
     fuck
    0.40
     capital
    0.38
     favorite
    0.38
     dates
    0.38
    hard
    0.38
    Activations Density 0.000%

    No Known Activations