© 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. 118637
    Prev
    Next
    INDEX
    Explanations

    a followed by an adjective/noun

    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
    Not in Any Lists

    No Comments

    Negative Logits
     hôtel
    -0.90
    Jetzt
    -0.89
    first
    -0.89
    Menschen
    -0.88
     oft
    -0.85
    Publications
    -0.85
    なので
    -0.83
     TRUE
    -0.82
    pr
    -0.82
     eventual
    -0.82
    POSITIVE LOGITS
     few
    1.27
     certain
    1.26
     kind
    1.19
     week
    1.13
     lot
    1.06
    ようです
    1.03
     month
    1.02
     cierta
    1.02
    だけではなく
    0.98
     Diony
    0.98
    Activations Density 0.012%

    No Known Activations