© 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. 8860
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign terms

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

    building success from failure

    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
    0.79
    on
    0.71
    s
    0.68
    es
    0.65
    *
    0.64
    {
    0.63
    ll
    0.62
    -
    0.61
    al
    0.60
    y
    0.59
    POSITIVE LOGITS
     व्यास
    0.61
     반지름
    0.60
     المصفوفه
    0.59
    પુર
    0.58
     गामा
    0.58
     spacerItem
    0.57
     фаразы
    0.57
     infecciones
    0.57
     reduzir
    0.57
     transportar
    0.57
    Activations Density 0.000%

    No Known Activations