© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3880
    Prev
    Next
    INDEX
    Explanations

    8x8 grid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     zcela
    1.86
     wszel
    1.76
    ଆ
    1.68
     naturl
    1.65
    全く
    1.64
     slto
    1.63
     quidem
    1.61
     moż
    1.61
     veoma
    1.60
    댜
    1.60
    POSITIVE LOGITS
    gr
    1.60
    grams
    1.48
    thorpe
    1.45
    k
    1.35
    bag
    1.33
    guards
    1.33
    god
    1.33
    addresses
    1.31
     Fields
    1.31
     branches
    1.30
    Activations Density 0.057%

    No Known Activations