© 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. 22-GEMMASCOPE-RES-131K
    7. 67825
    Prev
    Next
    INDEX
    Explanations

    orchestra

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

    This neuron detects references to orchestras, conductors, and related classical music performance terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    out
    -1.27
    )
    -1.26
    童年
    -1.25
    $
    -1.23
     nutritious
    -1.22
     conversations
    -1.20
            
    -1.20
     /
    -1.18
    ться
    -1.17
          
    -1.15
    POSITIVE LOGITS
    やろ
    1.58
     terce
    1.48
    başı
    1.45
    亊
    1.41
    <bos>
    1.39
    eſt
    1.32
    вають
    1.30
    🍪
    1.27
     budú
    1.25
    efore
    1.23
    Activations Density 0.021%

    No Known Activations