© 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. 103945
    Prev
    Next
    INDEX
    Explanations

    perception leading to strong feeling

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

    The neuron fires on words that describe strong, involuntary bodily reactions or visceral physical sensations (e.g. shudder, shiver, prickle).

    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
    ズム
    -0.91
     préférences
    -0.90
     sako
    -0.89
    ումներ
    -0.88
    igent
    -0.86
    માં
    -0.85
    enial
    -0.84
     viena
    -0.83
    нда
    -0.81
     positiva
    -0.81
    POSITIVE LOGITS
     at
    4.03
     upon
    2.19
     hearing
    2.13
     seeing
    2.02
    Seeing
    1.76
    upon
    1.66
    Upon
    1.61
    Hearing
    1.55
    seeing
    1.52
     Seeing
    1.52
    Activations Density 0.028%

    No Known Activations