© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 232711
    Prev
    Next
    INDEX
    Explanations

    weight loss and fatigue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conifers
    0.54
    ことから
    0.50
     compat
    0.49
     códigos
    0.48
    脇
    0.47
    志
    0.46
     restrictions
    0.45
     conces
    0.45
     canons
    0.45
    方式
    0.45
    POSITIVE LOGITS
    ០០
    0.53
    0
    0.47
    ávají
    0.46
     头
    0.45
    time
    0.45
     ভুট্টো
    0.45
    opedic
    0.44
     tah
    0.44
    wall
    0.44
    telling
    0.43
    Activations Density 0.000%

    No Known Activations