© 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. 33813
    Prev
    Next
    INDEX
    Explanations

    drum, drumming, eardrum, drumbeat

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

    The neuron activates on any token containing the substring “drum,” e.g. drum, drummer, drumming, tympanic, drumbeat, 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_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
    datalist
    -0.74
     チェック
    -0.73
    brium
    -0.72
     FCT
    -0.72
    ż
    -0.71
     blonde
    -0.67
    ɻ
    -0.66
    ツイ
    -0.65
    するという
    -0.64
    jén
    -0.63
    POSITIVE LOGITS
     drum
    3.78
     drums
    3.47
    drum
    3.25
     Drum
    3.20
    Drum
    3.16
     drumming
    2.69
    drums
    2.56
     Drums
    2.50
     DRUM
    2.41
    Drums
    2.39
    Activations Density 0.034%

    No Known Activations