© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63646
    Prev
    Next
    INDEX
    Explanations

    stage, performance, and narration

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

    The neuron fires on passages detailing the various artistic components or features of a performance (e.g. listing elements like languages, song, dance, acrobatics, 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
    ؒ
    -0.94
    siehe
    -0.94
    色々と
    -0.88
    rentes
    -0.87
    ligen
    -0.87
     informaron
    -0.86
     konsumen
    -0.85
     consacré
    -0.85
    Халы
    -0.84
    boîte
    -0.84
    POSITIVE LOGITS
     onstage
    2.20
     audience
    1.58
    audience
    1.29
     ensemble
    1.16
     Audience
    1.16
    Stage
    1.16
     performers
    1.10
     stage
    1.10
    Audience
    1.10
     pneus
    1.08
    Activations Density 0.015%

    No Known Activations