© 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. 29943
    Prev
    Next
    INDEX
    Explanations

    dé followed by French words

    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
     other
    -1.11
     traffico
    -1.02
     tempio
    -0.99
    <bos>
    -0.97
     attenzione
    -0.92
     irony
    -0.90
     frattempo
    -0.90
    boucles
    -0.90
     secretary
    -0.89
    相关的
    -0.89
    POSITIVE LOGITS
    って何
    1.07
     hesitating
    0.99
    AndFlush
    0.95
    jà
    0.94
    zda
    0.92
    mentes
    0.92
    cheiden
    0.92
    ೭
    0.91
    ENCER
    0.91
    さあ
    0.91
    Activations Density 0.006%

    No Known Activations