© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 7704
    Prev
    Next
    INDEX
    Explanations

    stop over or between cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ექტ
    0.45
    പ്പെട്ടി
    0.41
    ieten
    0.40
    PreferenceKeys
    0.39
    కాల
    0.38
    䁂
    0.37
    తె
    0.37
     來
    0.36
     بڑ
    0.36
     อื่น
    0.36
    POSITIVE LOGITS
     stops
    0.88
     Stops
    0.77
    stops
    0.77
     stop
    0.75
     stopping
    0.74
     dừng
    0.73
     towns
    0.72
     pause
    0.70
    停留
    0.69
     pauses
    0.69
    Activations Density 0.145%

    No Known Activations