© 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. 211387
    Prev
    Next
    INDEX
    Explanations

    head after

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

    AI, code, and image generation

    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
    ل
    0.62
    س
    0.55
    ल
    0.47
    ن
    0.45
    新
    0.45
    فعيل
    0.44
     আজ
    0.44
    sthrough
    0.44
    m
    0.44
    Baseline
    0.43
    POSITIVE LOGITS
     pisan
    0.54
     temi
    0.50
     konu
    0.48
    olean
    0.48
    тий
    0.48
     Faiz
    0.48
     सुप
    0.47
     sada
    0.47
    меч
    0.47
     Putri
    0.47
    Activations Density 0.001%

    No Known Activations