© 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. 76743
    Prev
    Next
    INDEX
    Explanations

    projects and locations

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

    objective and rhymes

    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
    ก
    0.48
    雁
    0.47
    ด
    0.45
    スピ
    0.45
    การ
    0.45
    Clock
    0.44
    강
    0.44
    삼
    0.43
    л
    0.43
    к
    0.43
    POSITIVE LOGITS
     painstakingly
    0.46
     implementação
    0.46
     پروژه
    0.45
    ட்டுகள்
    0.44
     nossas
    0.43
     projetos
    0.41
    ńskiej
    0.41
     extremamente
    0.41
     проекту
    0.41
     nuestras
    0.40
    Activations Density 0.002%

    No Known Activations