© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31415
    Prev
    Next
    INDEX
    Explanations

    engine power units

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

    The neuron fires on numerical measurements and units in vehicle or mechanical performance specifications (e.g. horsepower, engine displacement, torque, top speed).

    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
     [
    -0.90
    gex
    -0.86
    ={'
    -0.85
     enthält
    -0.85
     ท
    -0.84
     chứa
    -0.83
     і
    -0.81
    itrine
    -0.79
    amsmath
    -0.79
    إ
    -0.79
    POSITIVE LOGITS
     identically
    0.98
     output
    0.94
     sent
    0.94
     maximum
    0.92
     peak
    0.90
     unchanged
    0.88
     power
    0.87
     channeled
    0.84
    courtesy
    0.84
     potência
    0.82
    Activations Density 0.008%

    No Known Activations