© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3200
    Prev
    Next
    INDEX
    Explanations

    Key Features, Conversation Style, Test Data

    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_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ੰਜ
    0.41
    汜
    0.41
    יי
    0.40
     influencia
    0.40
    Ἔ
    0.39
    Ё
    0.39
     편성
    0.37
     بچه
    0.37
    நா
    0.37
    Ста
    0.37
    POSITIVE LOGITS
    ための
    0.48
    pinimg
    0.46
    pots
    0.45
    s
    0.44
    webapp
    0.44
    sz
    0.43
    ési
    0.43
    othelium
    0.43
     үш
    0.43
     ثانيه
    0.43
    Activations Density 0.151%

    No Known Activations