© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 21671
    Prev
    Next
    INDEX
    Explanations

    Ollama or similar LLM runners

    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
    ょ
    0.43
    <unused722>
    0.42
    追求
    0.41
    ョ
    0.40
     отлича
    0.40
     നിര
    0.38
     ई
    0.38
    руются
    0.38
     mimo
    0.38
    ເ
    0.38
    POSITIVE LOGITS
     Đảng
    0.41
    parties
    0.40
    yscale
    0.39
    supp
    0.38
    жкой
    0.38
    JavaScript
    0.37
    Worlds
    0.37
    run
    0.36
    hko
    0.36
    elect
    0.36
    Activations Density 0.001%

    No Known Activations