© 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. 58141
    Prev
    Next
    INDEX
    Explanations

    particle momentum and tracks

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

    This neuron detects mentions of a physics experimental facility location, specifically references to the Super Proton Synchrotron (SPS) at CERN.

    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
    viles
    -0.95
     didat
    -0.90
    zels
    -0.84
    ostructures
    -0.82
    动画
    -0.82
     suena
    -0.81
     volverá
    -0.81
    聲音
    -0.80
     trámite
    -0.78
    варе
    -0.77
    POSITIVE LOGITS
     tracks
    1.05
     track
    0.99
     momentum
    0.92
     Tracks
    0.79
     lab
    0.75
    track
    0.74
    Momentum
    0.73
    Tracks
    0.72
     thought
    0.71
    三月
    0.70
    Activations Density 0.016%

    No Known Activations