© 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. 29903
    Prev
    Next
    INDEX
    Explanations

    motorcycle gear and accessories

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

    The neuron fires on salient content words—especially the key nouns and terms (e.g. product names, body parts, feature descriptors) that carry most of the informational “weight” in a sentence.

    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
     suara
    -0.68
    stoy
    -0.67
    Harness
    -0.66
     kèo
    -0.65
     based
    -0.65
    зах
    -0.65
    blueprint
    -0.64
     hairstyles
    -0.64
     Spokes
    -0.64
     one
    -0.63
    POSITIVE LOGITS
     Motorcycle
    1.18
     motorcycle
    1.06
     accordion
    0.94
    artment
    0.92
     elbow
    0.90
    Motorcycle
    0.86
    gentes
    0.84
    bitro
    0.84
    STREET
    0.81
    Slide
    0.79
    Activations Density 0.003%

    No Known Activations