© 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. 10129
    Prev
    Next
    INDEX
    Explanations

    local areas

    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
     Grain
    1.01
     grain
    0.99
     grains
    0.98
    ([]);
    0.98
     lacked
    0.97
     والج
    0.97
    лять
    0.96
    geo
    0.95
     والب
    0.94
     பேர
    0.94
    POSITIVE LOGITS
    unst
    1.42
    эффици
    1.39
     onSubmit
    1.36
    wget
    1.36
     główn
    1.34
    র্ধ্ব
    1.29
    顼
    1.28
    Insert
    1.24
    rı
    1.23
    INTEGER
    1.23
    Activations Density 0.349%

    No Known Activations