© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6587
    Prev
    Next
    INDEX
    Explanations

    positive qualities and work ethic

    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_22_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
     Sloven
    0.99
     ग्ला
    0.99
     Kosovo
    0.98
     Malta
    0.96
    殖
    0.92
     Innsbruck
    0.87
     Ljubljana
    0.87
     Belgrade
    0.85
    uffer
    0.84
     Guernsey
    0.83
    POSITIVE LOGITS
     ICE
    1.10
    ICE
    1.07
     दीवार
    1.03
    cactus
    1.03
     DREAM
    1.02
    🌵
    0.98
    藤
    0.98
     cactus
    0.98
     taco
    0.97
     Nog
    0.97
    Activations Density 0.133%

    No Known Activations