© 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. 34527
    Prev
    Next
    INDEX
    Explanations

    vencedor, winner, grown, types, international

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

    limited resources, vulnerability

    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
     Elite
    0.54
    -
    0.52
     recharge
    0.52
    West
    0.49
    Server
    0.49
    World
    0.47
     AMP
    0.47
    衝
    0.47
    Elite
    0.46
     West
    0.46
    POSITIVE LOGITS
     vencedor
    0.54
     منصور
    0.49
     бази
    0.49
     viviendas
    0.49
     عباس
    0.48
     pdelay
    0.48
     ইন্দুর
    0.47
     வைத்து
    0.47
     дату
    0.47
     creciente
    0.47
    Activations Density 0.000%

    No Known Activations