© 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-262K
    7. 216026
    Prev
    Next
    INDEX
    Explanations

    international displayed

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

    no conflict, specific phrases

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     adenosine
    0.54
     erythrocytes
    0.49
     amus
    0.49
     assimilation
    0.48
     viewing
    0.48
     aquilo
    0.46
    Denis
    0.45
    牟
    0.45
     assimilated
    0.45
     chấp
    0.44
    POSITIVE LOGITS
    rees
    0.52
    संबंध
    0.50
    违反
    0.48
    itons
    0.48
    ähr
    0.45
    र्स
    0.45
    ild
    0.45
     बुन
    0.44
    acées
    0.43
     आंसू
    0.43
    Activations Density 0.000%

    No Known Activations