© 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. 16772
    Prev
    Next
    INDEX
    Explanations

    companies and sports teams

    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
     this
    -1.64
     before
    -1.49
     there
    -1.36
     they
    -1.25
     after
    -1.17
     porcent
    -1.17
     had
    -1.11
     includes
    -1.10
     comes
    -1.09
     даже
    -1.09
    POSITIVE LOGITS
    andering
    1.23
     largely
    1.23
     broader
    1.22
    ara
    1.20
     immense
    1.20
    referred
    1.20
     somewhat
    1.19
    za
    1.18
    played
    1.15
     daugiau
    1.15
    Activations Density 0.030%

    No Known Activations