© 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. 227897
    Prev
    Next
    INDEX
    Explanations

    welcome you

    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
    дык
    0.48
    就可以了
    0.47
    первых
    0.46
    r
    0.44
    푼
    0.44
    ر
    0.44
    ニー
    0.43
    ʦ
    0.43
     успе
    0.42
    確率
    0.41
    POSITIVE LOGITS
     Drawer
    0.52
     Shooting
    0.47
     ഷോ
    0.47
     सैन्य
    0.47
     เครื่อง
    0.45
     हर
    0.45
     హై
    0.45
     Builders
    0.45
     Bildern
    0.44
    ashing
    0.43
    Activations Density 0.001%

    No Known Activations