© 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. 93680
    Prev
    Next
    INDEX
    Explanations

    performances and music

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

    The neuron responds to substantive content words—mostly nouns and adjectives—rather than to common function words.

    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
    versorgung
    -0.77
    Artic
    -0.77
     dinners
    -0.77
    žiai
    -0.75
     Tour
    -0.75
     toured
    -0.74
     Actors
    -0.73
    キャラ
    -0.73
    iolis
    -0.73
    AMAHA
    -0.73
    POSITIVE LOGITS
     performance
    2.97
     performances
    2.86
    performance
    2.11
    Performance
    1.92
    perform
    1.86
     Performances
    1.84
     PERFORMANCE
    1.84
    表演
    1.78
     numbers
    1.77
    Performances
    1.75
    Activations Density 0.021%

    No Known Activations