© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6931
    Prev
    Next
    INDEX
    Explanations

    rustling of leaves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pamo
    1.33
    sgem
    1.32
    andowski
    1.29
    줍
    1.28
     žel
    1.27
    ontaneous
    1.26
    routed
    1.24
     tenang
    1.24
    adeon
    1.23
    annulation
    1.22
    POSITIVE LOGITS
    tı
    1.28
    tım
    1.13
     οποία
    1.06
    Quan
    1.06
    ابط
    1.03
    mation
    1.03
    rootScope
    1.02
    ([],
    1.02
     deficit
    1.02
     Meghna
    1.01
    Activations Density 0.152%

    No Known Activations