© 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. 12067
    Prev
    Next
    INDEX
    Explanations

    facial redness and blushing

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

    The neuron fires on terms that describe facial reddening (e.g. blush, flushing, red-faced).

    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
    adena
    -0.80
    uppercase
    -0.73
    voirs
    -0.73
    撕
    -0.72
    rain
    -0.72
     Sorrow
    -0.72
    мови
    -0.71
    сота
    -0.69
    åne
    -0.69
    binding
    -0.68
    POSITIVE LOGITS
     blush
    3.33
     blushing
    3.30
     blushed
    3.16
    blush
    2.39
     flushed
    2.38
     cheeks
    2.22
     redd
    2.14
     red
    2.00
     flushing
    1.95
     redness
    1.93
    Activations Density 0.014%

    No Known Activations