© 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-16K
    7. 1367
    Prev
    Next
    INDEX
    Explanations

    lists and diverse languages

    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_16k_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
    л
    1.78
    از
    1.65
    u
    1.57
    ০০০
    1.49
     monolayer
    1.49
    וכ
    1.48
    Notwithstanding
    1.46
    teile
    1.44
    corn
    1.43
    ayani
    1.42
    POSITIVE LOGITS
    년대
    1.68
    s
    1.58
     ellipsis
    1.53
    न
    1.53
    $('#
    1.52
    ""
    1.43
    ,*/}
    1.41
     Gericht
    1.39
     allons
    1.39
     Atual
    1.38
    Activations Density 0.388%

    No Known Activations