© 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. 155223
    Prev
    Next
    INDEX
    Explanations

    gender and age

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

    biological and chemical processes

    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
    on
    0.58
    מ
    0.55
    p
    0.54
    W
    0.52
    T
    0.52
    A
    0.52
    म
    0.51
    N
    0.49
    Bla
    0.49
    ρα
    0.49
    POSITIVE LOGITS
     কন্যা
    0.55
     четы
    0.54
     perempuan
    0.54
     gyerek
    0.53
     CHILDREN
    0.51
     குழந்த
    0.50
     குழந்தை
    0.50
     Preschool
    0.50
     screenSize
    0.50
     രണ്ട്
    0.49
    Activations Density 0.002%

    No Known Activations