© 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. 47525
    Prev
    Next
    INDEX
    Explanations

    ensemble performing arts groups

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

    The neuron fires strongly on numerical tokens and list‐style markers (digits, years, colons, parentheses), i.e. elements used for structured lists or dates.

    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
     theater
    -0.91
     commander
    -0.82
     theatre
    -0.80
    Producers
    -0.77
    users
    -0.77
     estacion
    -0.76
    ⌟
    -0.76
    theater
    -0.75
    vény
    -0.74
    getTransaction
    -0.74
    POSITIVE LOGITS
     chorus
    2.14
     ensemble
    1.82
    chorus
    1.55
     Chorus
    1.50
     Ensemble
    1.40
    Chorus
    1.28
    ensemble
    1.24
     corps
    1.21
    corps
    1.17
     featured
    1.16
    Activations Density 0.017%

    No Known Activations