© 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. 22-GEMMASCOPE-RES-131K
    7. 64415
    Prev
    Next
    INDEX
    Explanations

    social invitations and events

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     fiyat
    -0.98
     Judiciary
    -0.90
    missing
    -0.81
     وكل
    -0.79
     Macau
    -0.79
     Charger
    -0.79
     missing
    -0.78
    ősz
    -0.78
    lags
    -0.77
     možno
    -0.77
    POSITIVE LOGITS
     invited
    1.44
    お試し
    1.07
     tonight
    1.04
     visit
    1.00
     visiting
    0.98
     today
    0.96
     hosted
    0.94
    litch
    0.94
    今回
    0.93
     hosting
    0.93
    Activations Density 0.166%

    No Known Activations