© 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. 2973
    Prev
    Next
    INDEX
    Explanations

    encrypted or open

    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
    ت
    1.69
    hm
    1.53
    in
    1.48
    hmm
    1.47
    ନ୍ତି
    1.41
    at
    1.39
    as
    1.38
    т
    1.37
    anesulfonyl
    1.34
    න්න
    1.33
    POSITIVE LOGITS
     romp
    1.38
     dicht
    1.37
     угодно
    1.37
    <bos>
    1.35
     stain
    1.30
    pecial
    1.30
     ہوئی
    1.27
     porosity
    1.27
    elfalt
    1.24
     ventre
    1.23
    Activations Density 0.295%

    No Known Activations