© 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. 118002
    Prev
    Next
    INDEX
    Explanations

    acknowledgement or mild surprise

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

    This neuron detects short discourse markers and related punctuation (e.g. “Oh,” “ok,” “So,” “.”, “?”).

    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
     besonders
    -0.97
    irmish
    -0.90
    どうか
    -0.83
     or
    -0.80
     इसमें
    -0.78
    tsz
    -0.77
    קד
    -0.76
     especialmente
    -0.74
     here
    -0.74
    .$,
    -0.73
    POSITIVE LOGITS
     understood
    2.14
    なるほど
    1.95
    Gotcha
    1.82
    Understood
    1.77
     then
    1.77
     gotcha
    1.72
     понятно
    1.66
    明白了
    1.60
    understood
    1.60
     understanding
    1.59
    Activations Density 0.010%

    No Known Activations