© 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. 63804
    Prev
    Next
    INDEX
    Explanations

    CNC and numerical control

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

    The neuron is triggered by technical references to machine tools—especially computer-controlled (CNC) contouring and positioning systems.

    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
    團體
    -0.83
    chute
    -0.76
     lunghezza
    -0.71
     persoane
    -0.71
    clown
    -0.70
    Тут
    -0.69
     transmembrane
    -0.68
     нема
    -0.67
    cuadro
    -0.66
     rectangular
    -0.66
    POSITIVE LOGITS
     CNC
    1.39
     axis
    1.23
     drilling
    1.13
    axis
    1.12
    controlled
    1.10
     NC
    1.04
     Axis
    1.04
     controlled
    1.02
     milling
    1.01
     numerically
    1.01
    Activations Density 0.075%

    No Known Activations