© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23963
    Prev
    Next
    INDEX
    Explanations

    money from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    令人
    0.60
     באמצעות
    0.57
     coloro
    0.55
    被称为
    0.54
    人々
    0.53
    ˈ
    0.52
     প্রকৃতপক্ষে
    0.52
    ̕
    0.52
     véritable
    0.51
     („
    0.51
    POSITIVE LOGITS
     чтоб
    0.82
     +-
    0.74
     trochę
    0.73
     خیلی
    0.72
     такой
    0.68
     думаю
    0.68
     там
    0.67
     +
    0.67
     менять
    0.67
     туда
    0.66
    Activations Density 0.003%

    No Known Activations