© 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. 103525
    Prev
    Next
    INDEX
    Explanations

    body composition and mass

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

    The neuron fires on phrases referring to body composition measures—especially “body weight,” “lean body mass,” and related mass metrics.

    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
    Evid
    -0.77
     hưng
    -0.77
     演
    -0.76
     microfilm
    -0.75
    chelle
    -0.75
     Exploitation
    -0.71
     Knowles
    -0.71
    唇
    -0.71
    ี่ยว
    -0.69
     begyn
    -0.69
    POSITIVE LOGITS
     Body
    1.36
     body
    1.34
     fat
    1.20
     Siri
    1.16
     BODY
    1.14
    Body
    1.09
     visceral
    1.08
    Fat
    1.04
    fat
    1.02
     Fat
    1.02
    Activations Density 0.118%

    No Known Activations