© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106270
    Prev
    Next
    INDEX
    Explanations

    US place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    cvt
    -0.91
    כב
    -0.75
     compatriots
    -0.75
    ঙ্
    -0.73
    spend
    -0.72
    LEAVE
    -0.71
    PERIOD
    -0.70
     νό
    -0.70
     več
    -0.70
     tłuma
    -0.70
    POSITIVE LOGITS
     Fayetteville
    1.36
     Lumber
    0.89
    فی
    0.76
     Wilmington
    0.74
    Ŋ
    0.73
    Ren
    0.72
    ✡
    0.72
     Fairmont
    0.72
    جام
    0.72
    RES
    0.72
    Activations Density 0.016%

    No Known Activations