© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11555
    Prev
    Next
    INDEX
    Explanations

    improvement

    np_acts-logits-general · gemini-2.5-flash-lite

    improving something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
     rozpoczę
    0.69
     senjata
    0.64
     Ż
    0.61
     inici
    0.61
     rozší
    0.57
     as
    0.56
     řek
    0.56
    </strong>
    0.55
    0.55
     aktif
    0.55
    POSITIVE LOGITS
    改善
    1.03
    Improve
    1.00
    improvement
    0.95
     improving
    0.94
     Improvement
    0.92
    improved
    0.92
     improvement
    0.91
    Improved
    0.91
     개선
    0.89
     improved
    0.89
    Activations Density 0.346%

    No Known Activations