© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2917
    Prev
    Next
    INDEX
    Explanations

    dialogue/script markers

    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
    Negative Logits
     Concordia
    1.43
    达到
    1.42
     Estos
    1.37
     witchcraft
    1.36
    ...\...\...\...\
    1.36
    墾
    1.34
     Yangzhou
    1.31
     تعالى
    1.29
     忄
    1.29
     totalSupply
    1.29
    POSITIVE LOGITS
    siehe
    1.20
     surtout
    1.14
    сет
    1.14
     बजाय
    1.13
     kilku
    1.12
    ्न
    1.09
    eb
    1.09
    en
    1.08
    eer
    1.08
    ाये
    1.07
    Activations Density 0.138%

    No Known Activations