© 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. 106829
    Prev
    Next
    INDEX
    Explanations

    pronunciation and articulation of speech

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

    The neuron primarily activates on formal, technical definition or explanation passages in expository text.

    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
     translated
    -0.76
    NX
    -0.73
    Translation
    -0.73
     Thü
    -0.72
     midi
    -0.71
    Ix
    -0.70
    }{@
    -0.70
    ingat
    -0.70
    ئية
    -0.69
    ụp
    -0.68
    POSITIVE LOGITS
     pronunciation
    2.77
    pron
    1.98
     articulation
    1.98
     pronunci
    1.90
     Pron
    1.85
     pronounce
    1.74
     pron
    1.73
    Pronunciation
    1.68
     artic
    1.67
    Pron
    1.59
    Activations Density 0.058%

    No Known Activations