© 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. 30211
    Prev
    Next
    INDEX
    Explanations

    Cassandra Peterson, Columbia Center, Medlog, Q:

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

    The neuron strongly activates on cooking‐related terms—especially ingredient names and their associated quantities or measurements in recipes.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    qiang
    -0.94
    创始人
    -0.94
    łem
    -0.92
     Terima
    -0.91
    menschen
    -0.91
     miniaturka
    -0.91
     tunik
    -0.90
    gracias
    -0.89
     fizik
    -0.88
     разрабо
    -0.87
    POSITIVE LOGITS
    ıda
    1.02
     wrongly
    0.89
    closure
    0.85
    eyn
    0.84
     extent
    0.82
     clicks
    0.81
    mfenced
    0.78
    君は
    0.78
     coarse
    0.77
     mentioned
    0.76
    Activations Density 0.006%

    No Known Activations