© 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. 92373
    Prev
    Next
    INDEX
    Explanations

    American places and technology

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

    American United States

    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
     ឬ
    0.53
     ValidationError
    0.49
     または
    0.47
     ಅಥವಾ
    0.45
     или
    0.45
     ਜਾਂ
    0.44
     或
    0.43
     किंवा
    0.41
     CONSEQUENTIAL
    0.41
    죵
    0.41
    POSITIVE LOGITS
     американ
    0.43
    捃
    0.42
    Photo
    0.41
     aant
    0.41
     hải
    0.40
     amerikanischen
    0.40
    美国
    0.40
     últimos
    0.40
     এসেছেন
    0.40
     oysters
    0.39
    Activations Density 0.000%

    No Known Activations