© 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. 62784
    Prev
    Next
    INDEX
    Explanations

    bicycle parts and brands

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

    This neuron is strongly triggered by the repeated appearance of the brand name “Bontrager.”

    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
     slots
    -0.79
    isantes
    -0.79
     Ejemplo
    -0.79
     plumber
    -0.77
    elis
    -0.77
     slot
    -0.76
    дәбият
    -0.76
     qPCR
    -0.76
    Tē
    -0.75
    Revenue
    -0.74
    POSITIVE LOGITS
     frame
    0.80
     Frame
    0.78
    Frame
    0.73
     health
    0.73
     Swat
    0.72
     loves
    0.71
     medical
    0.70
    frame
    0.69
    чется
    0.69
    xw
    0.68
    Activations Density 0.014%

    No Known Activations