© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90139
    Prev
    Next
    INDEX
    Explanations

    upper/lower body regions

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

    This neuron detects mentions of specific anatomical body regions, especially upper or lower parts (e.g. “lower back,” “upper body”).

    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
    SIDE
    -1.03
     SIDE
    -0.89
    Side
    -0.82
     side
    -0.82
    side
    -0.81
     chr
    -0.80
    mydb
    -0.79
    ța
    -0.78
     republics
    -0.77
    ਤ
    -0.76
    POSITIVE LOGITS
     body
    1.35
     part
    1.23
     portion
    1.06
     half
    1.03
    Body
    1.00
    portion
    0.95
    body
    0.93
     трен
    0.87
     Parlamento
    0.87
     Teil
    0.86
    Activations Density 0.035%

    No Known Activations