© 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. 146184
    Prev
    Next
    INDEX
    Explanations

    complimentary wireless internet

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

    use and restrictions

    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
    অপহরণ
    0.46
    
    0.43
     perjalanan
    0.43
    শুধ
    0.41
    jeća
    0.40
     সত্যিকারের
    0.40
     ኩ
    0.40
     Acá
    0.40
     Rohing
    0.39
    Сегодня
    0.39
    POSITIVE LOGITS
     Turner
    0.42
     Atomic
    0.42
    Turner
    0.40
    eras
    0.39
     ->
    0.39
    ীক
    0.39
    ビュー
    0.38
     senc
    0.38
     NT
    0.38
    INTE
    0.37
    Activations Density 0.041%

    No Known Activations