© 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. 106374
    Prev
    Next
    INDEX
    Explanations

    financial, medical, and declarative sentences

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

    The neuron fires strongly on the legal‐boilerplate connective “with respect to.”

    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
    Siapa
    -0.81
    高雄
    -0.79
    Он
    -0.75
     headlamp
    -0.74
     evidently
    -0.73
    kell
    -0.73
     entity
    -0.72
     repayments
    -0.72
    OptionPane
    -0.72
    IsContent
    -0.72
    POSITIVE LOGITS
     beren
    0.89
    Pn
    0.87
     aspek
    0.85
     藏
    0.81
    dR
    0.81
     moza
    0.80
     accrued
    0.79
     karton
    0.78
     BLACK
    0.76
     板
    0.76
    Activations Density 0.015%

    No Known Activations