© 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. 31120
    Prev
    Next
    INDEX
    Explanations

    code (especially neural networks) or specific words

    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
    už
    0.40
     transmembrane
    0.39
     átomos
    0.37
    ácter
    0.37
     Už
    0.37
    αιν
    0.37
     Tolerance
    0.37
     Rais
    0.36
     Asalamualaikum
    0.36
    POSITIVE LOGITS
     脚
    0.42
    fins
    0.41
    ftop
    0.41
     ft
    0.39
     ав
    0.37
    ft
    0.36
     FOOT
    0.36
     Swindon
    0.36
     Ant
    0.36
    devkit
    0.36
    Activations Density 0.001%

    No Known Activations