© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12103
    Prev
    Next
    INDEX
    Explanations

    Uni and subsequent words

    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
    з
    3.09
    ്യ
    2.78
    hjust
    2.76
     estrada
    2.74
     naturels
    2.72
    ۰۰
    2.62
    ین
    2.58
    ỡi
    2.57
    uing
    2.55
    paces
    2.54
    POSITIVE LOGITS
    (.*
    2.68
    在
    2.55
     upped
    2.53
     MALDI
    2.53
     Размер
    2.52
    Ро
    2.50
     acetylation
    2.50
    tegr
    2.49
    ₕ
    2.46
     måde
    2.45
    Activations Density 0.002%

    No Known Activations