© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161891
    Prev
    Next
    INDEX
    Explanations

    activity types

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

    android activity code

    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
     in
    0.61
    idar
    0.57
    ami
    0.53
    কাতে
    0.51
    ల
    0.51
    esha
    0.50
     articles
    0.50
    लिंग
    0.50
    ()=>{
    0.50
    বাহিনী
    0.50
    POSITIVE LOGITS
    y
    0.79
    né
    0.68
    не
    0.64
    ע
    0.59
    t
    0.58
     příjem
    0.57
    lieder
    0.56
    W
    0.54
     laquelle
    0.53
    g
    0.53
    Activations Density 0.000%

    No Known Activations