© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9722
    Prev
    Next
    INDEX
    Explanations

    en.wikipedia.org/wiki/

    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_9_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
    न
    3.06
    ரா
    2.94
    ت
    2.85
    要
    2.80
    Resize
    2.73
     ulcer
    2.63
    לב
    2.56
     measles
    2.54
     telesc
    2.48
     NVIC
    2.47
    POSITIVE LOGITS
    amaya
    2.68
    ון
    2.61
    ható
    2.52
     त्यावेळी
    2.45
    торая
    2.37
    东西
    2.34
    開催
    2.30
    ৭
    2.29
    Leaks
    2.28
    образной
    2.25
    Activations Density 0.013%

    No Known Activations