© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 19069
    Prev
    Next
    INDEX
    Explanations

    detention or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     Provisions
    0.75
    તન
    0.73
    崬
    0.72
    тира
    0.72
     utmost
    0.72
    මණ
    0.72
     illustrazione
    0.71
     цвет
    0.71
     серд
    0.70
     pups
    0.70
    POSITIVE LOGITS
    నం
    0.93
     geng
    0.83
    roscopic
    0.75
    気軽
    0.75
    |
    0.74
    本书
    0.72
    lumat
    0.71
    እ
    0.69
     तक्र
    0.69
     deliberately
    0.68
    Activations Density 0.000%

    No Known Activations