© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84220
    Prev
    Next
    INDEX
    Explanations

    expressing praise and congratulations

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

    The main thing this neuron does is detect exclamatory praise or congratulatory expressions (e.g. “Good job,” “Bravo,” “Slow clap,” “Nice work,” “Congratulations,” etc.).

    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
     in
    -1.88
    より
    -1.48
     from
    -1.45
    杙
    -1.41
     drei
    -1.41
     of
    -1.40
    についての
    -1.40
     Lots
    -1.36
    攫
    -1.33
     \\
    -1.30
    POSITIVE LOGITS
    👏
    1.80
    👏👏
    1.66
    あの
    1.59
    </b>
    1.56
    nicze
    1.52
    カレンダー
    1.49
     Joaqu
    1.48
     simila
    1.46
    tható
    1.43
     réussir
    1.43
    Activations Density 0.021%

    No Known Activations