© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35265
    Prev
    Next
    INDEX
    Explanations

    strengthening muscles and body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     উজ্জ্বল
    0.38
    袤
    0.38
     Indicators
    0.38
    ulları
    0.37
     リュ
    0.36
    Zx
    0.36
     assumptive
    0.36
    izi
    0.36
     महसूस
    0.35
    macosx
    0.35
    POSITIVE LOGITS
    Prior
    0.42
     prior
    0.40
    prior
    0.38
    нын
    0.37
    裳
    0.37
    لاف
    0.36
     vorher
    0.36
    Keywords
    0.35
    сем
    0.35
    ceed
    0.35
    Activations Density 0.029%

    No Known Activations