© 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. 235885
    Prev
    Next
    INDEX
    Explanations

    GPS tracking

    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
     लड्डू
    0.54
    र्मेंद्र
    0.49
    繕
    0.47
    ൧
    0.47
    閉じ
    0.46
    主に
    0.45
    部屋
    0.45
    初心
    0.45
    괵
    0.44
    ಮಾ
    0.44
    POSITIVE LOGITS
     ส่ง
    0.52
     Casting
    0.50
     transpos
    0.47
    firm
    0.46
     น้ำ
    0.46
     spectacularly
    0.45
    barg
    0.45
     Firm
    0.45
     firm
    0.44
     สร้าง
    0.44
    Activations Density 0.000%

    No Known Activations