© 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. 4042
    Prev
    Next
    INDEX
    Explanations

    custom code or implementations

    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
     致
    2.43
     血
    2.38
     manned
    2.36
    <unused1171>
    2.33
    <unused1182>
    2.29
    𒅗
    2.28
     含
    2.27
     多
    2.27
     已
    2.26
     长
    2.25
    POSITIVE LOGITS
    ucristo
    2.14
    ir
    2.04
     iyo
    1.97
    ž
    1.96
     neuen
    1.96
    java
    1.92
    RichEmbed
    1.92
    jQuery
    1.92
    constexpr
    1.90
    jogo
    1.87
    Activations Density 0.123%

    No Known Activations