© 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. 14192
    Prev
    Next
    INDEX
    Explanations

    main aspect identification

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

    core ideas and strategy

    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
     Highness
    0.64
     рождения
    0.63
    '
    0.58
     neki
    0.58
     barbit
    0.58
     ⚫
    0.57
     acaba
    0.57
     spineItem
    0.55
     agradable
    0.55
     verificar
    0.55
    POSITIVE LOGITS
     ዋና
    0.79
    主
    0.75
    main
    0.74
     main
    0.70
    stays
    0.68
     اصلی
    0.67
     मुख्य
    0.66
     principaux
    0.66
    وا
    0.65
     principais
    0.64
    Activations Density 0.040%

    No Known Activations