© 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. 2439
    Prev
    Next
    INDEX
    Explanations

    is/are followed by description

    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
    comes
    1.66
    ра
    1.66
    s
    1.64
    P
    1.47
    ↵↵
    1.46
     ہیں۔
    1.45
    的是
    1.38
     Of
    1.32
    раст
    1.28
    part
    1.28
    POSITIVE LOGITS
    ST
    1.50
    ૂર્વ
    1.44
    ̰
    1.42
     보
    1.40
    ských
    1.38
     doskona
    1.36
    িং
    1.35
    ⇉
    1.33
    JlcG
    1.29
    <s>
    1.29
    Activations Density 0.234%

    No Known Activations