© 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. 68605
    Prev
    Next
    INDEX
    Explanations

    exam preparation materials

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

    can chat

    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
     Jia
    0.41
     वक़्त
    0.41
    жкой
    0.41
    灼
    0.40
    mixin
    0.40
     Chengdu
    0.40
    ที่ไม่
    0.40
    味噌
    0.39
    matory
    0.39
     Zeng
    0.39
    POSITIVE LOGITS
     carc
    0.45
    ̆
    0.41
    ныгы
    0.41
    벤트
    0.40
    പാട
    0.40
     determinar
    0.39
     sonra
    0.39
     carv
    0.38
     lös
    0.38
     selles
    0.38
    Activations Density 0.005%

    No Known Activations