© 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. 129610
    Prev
    Next
    INDEX
    Explanations

    mashed potatoes

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

    object detection models

    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
    Negative Logits
     Elke
    0.54
    adale
    0.52
    İlk
    0.50
    बित
    0.50
    pital
    0.50
    Κα
    0.49
     சமீ
    0.49
     abrog
    0.48
    ग
    0.48
     seleccion
    0.47
    POSITIVE LOGITS
     。,
    0.47
     .,
    0.40
     موجود
    0.39
     نبود
    0.39
     cartes
    0.39
     щоб
    0.38
    uten
    0.38
    ropathy
    0.38
     HAM
    0.38
     شه
    0.38
    Activations Density 0.001%

    No Known Activations