© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8514
    Prev
    Next
    INDEX
    Explanations

    sensorimotor system qualities

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

    medical and technical terms related to sensory systems, particularly "sensorineural" and "sensorimotor".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects subword occurrences of “sensor” (and its derivative forms like sensorineural, sensorless, sensory-, sensorimotor) in technical terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Would
    -2.08
    したのは
    -1.64
     πρέπει
    -1.63
    ˧
    -1.59
     rampant
    -1.57
    してみました
    -1.55
    瑷
    -1.52
    分に
    -1.51
    馀
    -1.50
     nur
    -1.49
    POSITIVE LOGITS
    鹛
    1.91
    
    1.88
    B
    1.83
    这不
    1.80
    衚
    1.79
    铪
    1.70
     continúas
    1.69
     wich
    1.69
    囹
    1.60
    岜
    1.58
    Activations Density 0.056%

    No Known Activations