© 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. 81412
    Prev
    Next
    INDEX
    Explanations

    negotiated social experiences

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

    This neuron specializes in detecting mentions of bodily experiences—especially phrases like “women’s bodily experiences.”

    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
    unate
    -0.95
    なければならない
    -0.90
    ='')
    -0.89
    ueel
    -0.85
    nelle
    -0.85
    mentaire
    -0.84
    thane
    -0.83
    "];
    -0.83
     tổng
    -0.83
     JUN
    -0.82
    POSITIVE LOGITS
     meanings
    1.58
     strategies
    1.53
     practices
    1.43
     negotiated
    1.30
     negotiation
    1.24
     spaces
    1.20
     constructed
    1.18
     negotiate
    1.17
     constructing
    1.15
     meaning
    1.13
    Activations Density 0.054%

    No Known Activations