© 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. 47019
    Prev
    Next
    INDEX
    Explanations

    dog breeds

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on animal breed names (e.g. Chow, Bulldog, Boxer, Mastiff, Scottish Fold, German Lop).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
     Laboratories
    -0.79
     labs
    -0.77
     poodle
    -0.77
     Labs
    -0.73
     York
    -0.73
    ⣠
    -0.73
     लेख
    -0.72
     thingy
    -0.72
    exif
    -0.69
     lab
    -0.69
    POSITIVE LOGITS
     bulldog
    1.22
     bull
    1.22
    BULL
    1.18
    Bull
    1.16
     Bulldog
    1.15
    bull
    1.13
     BULL
    1.10
     Bull
    1.10
     Bulldogs
    1.00
     wrink
    0.97
    Activations Density 0.011%

    No Known Activations