© 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. 106190
    Prev
    Next
    INDEX
    Explanations

    brit or brittany names and places

    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
    Consejos
    -0.80
     ře
    -0.79
     guessed
    -0.76
    outchou
    -0.71
    sx
    -0.70
    ἑ
    -0.70
    Duk
    -0.69
     inflated
    -0.69
    skull
    -0.68
     suficientes
    -0.67
    POSITIVE LOGITS
    Brit
    1.01
     Brit
    0.93
    nell
    0.84
    Crossref
    0.82
    ney
    0.82
    抬
    0.81
    brit
    0.81
     acest
    0.79
    luence
    0.79
     abroad
    0.78
    Activations Density 0.012%

    No Known Activations