© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117081
    Prev
    Next
    INDEX
    Explanations

    "duh"

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

    The neuron selectively fires on informal, often sarcastic or dismissive interjections and phrases (e.g. “duh,” “no **** Sherlock,” “HA,” “I feel a little dumb”), signaling obvious-statement or mocking tones.

    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
    ❼
    -0.84
     jednom
    -0.81
     NUKAT
    -0.81
     vred
    -0.79
     zni
    -0.79
     historie
    -0.78
    rı
    -0.78
    btns
    -0.76
    嗲
    -0.76
    sü
    -0.73
    POSITIVE LOGITS
     duh
    4.50
    duh
    3.97
    Duh
    3.88
     DU
    3.59
     Du
    3.56
    DU
    2.73
    Du
    2.70
     du
    2.63
    du
    2.11
     ду
    2.08
    Activations Density 0.034%

    No Known Activations