© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    lines and code lines

    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
    nya
    4.15
    stained
    4.03
    ことができる
    3.73
    н
    3.49
    ことができます
    3.46
    ときの
    3.34
    discovered
    3.31
    ные
    3.30
    د
    3.29
    ness
    3.29
    POSITIVE LOGITS
    e
    4.66
    ٔ
    4.07
    ece
    3.73
    ться
    3.15
    en
    3.13
    hmen
    3.12
    ysel
    3.12
    eee
    3.11
     staw
    3.06
    eeee
    3.00
    Activations Density 1.180%

    No Known Activations