© 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. 10-GEMMASCOPE-RES-131K
    7. 104349
    Prev
    Next
    INDEX
    Explanations

    what a [adjective/noun] exclamation

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

    This neuron flags the head noun in exclamatory “What a …” or “What an …” phrases.

    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
    鈇
    -2.52
     miljoner
    -2.30
    箧
    -2.27
     of
    -2.14
    衚
    -2.13
     millioner
    -2.03
     minutter
    -2.02
    觧
    -2.00
     tantangan
    -1.99
     手順
    -1.95
    POSITIVE LOGITS
    </b>
    2.05
     cherish
    1.88
     rotten
    1.84
    憷
    1.83
    赚钱
    1.78
    蛰
    1.77
     â
    1.70
     glor
    1.69
     fuckin
    1.69
    ↵
    1.68
    Activations Density 0.003%

    No Known Activations