© 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. 117633
    Prev
    Next
    INDEX
    Explanations

    linear motion and motors

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

    The neuron looks for the formal, patent-style technical specification language (e.g. “Field of the Invention,” numbered sections, and mechanical/engineering descriptors).

    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
    胄
    -0.83
    Жи
    -0.80
    shed
    -0.74
    した場合
    -0.73
    িস
    -0.71
    }`}>
    -0.71
     njego
    -0.71
     Antwerpen
    -0.70
     začet
    -0.70
     القد
    -0.69
    POSITIVE LOGITS
     motion
    1.21
     backlash
    1.07
     Motion
    1.04
     encoder
    1.02
     preload
    0.99
     servo
    0.90
    motion
    0.89
     gan
    0.89
    Motion
    0.89
     Bewegung
    0.89
    Activations Density 0.051%

    No Known Activations