© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43907
    Prev
    Next
    INDEX
    Explanations

    body

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

    The neuron strongly activates on mentions of the word “body,” i.e. references to the human 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_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
    赑
    -2.17
     wła
    -1.53
     senjata
    -1.50
    
    -1.50
    𓆸
    -1.49
    玙
    -1.46
    푁
    -1.45
    鹮
    -1.45
     ONCE
    -1.45
     그의
    -1.43
    POSITIVE LOGITS
    /
    1.54
    了一口
    1.45
     how
    1.45
    —
    1.38
    ”
    1.38
     why
    1.38
    wide
    1.37
    У
    1.37
     comanda
    1.37
    的设计
    1.34
    Activations Density 0.038%

    No Known Activations