© 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. 245494
    Prev
    Next
    INDEX
    Explanations

    left orset whenmouth ,USB charging

    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
    0.58
    ر
    0.52
    ล
    0.46
    ritt
    0.45
    รั
    0.44
     تہ
    0.43
    ز
    0.43
    yll
    0.42
    त्याने
    0.42
    on
    0.41
    POSITIVE LOGITS
    {*
    0.50
     pasión
    0.49
     estación
    0.47
     probar
    0.46
     sábado
    0.46
     Maroon
    0.46
     Salvador
    0.46
     অনিশ্চ
    0.45
     inescapable
    0.44
     Aquí
    0.44
    Activations Density 0.001%

    No Known Activations