© 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. 133158
    Prev
    Next
    INDEX
    Explanations

    patients utilizing apps

    np_acts-logits-general · gemini-2.5-flash-lite

    AI, volatile, cooking, animals

    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
    e
    0.66
    o
    0.57
    i
    0.51
    ice
    0.48
    U
    0.48
    RESOURCE
    0.46
    resource
    0.46
    ce
    0.45
     Mutation
    0.45
    T
    0.45
    POSITIVE LOGITS
     zub
    0.50
     ત્રણ
    0.50
     límites
    0.49
     واحدة
    0.49
    兩種
    0.49
    ujen
    0.48
     يوم
    0.47
     swirls
    0.46
     endothelial
    0.46
    ParamNum
    0.46
    Activations Density 0.000%

    No Known Activations