© 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. 78309
    Prev
    Next
    INDEX
    Explanations

    pronunciation and how words are said

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

    The neuron activates on pronunciation and phonetics cues (e.g. “Pronunciation,” “pronounced,” “phonemes”).

    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
    TUAL
    -0.99
    TRIBUTES
    -0.84
    uinal
    -0.81
    Olá
    -0.80
    ̠
    -0.79
    ֶּ
    -0.75
    สาร
    -0.75
     använda
    -0.74
     currentDate
    -0.73
     Durchmesser
    -0.73
    POSITIVE LOGITS
     pronunciation
    1.74
     pronounce
    1.68
    pron
    1.59
     pronouncing
    1.45
     pronunci
    1.44
     Pron
    1.41
     phonetic
    1.33
     syllables
    1.22
     pron
    1.20
    Pron
    1.18
    Activations Density 0.029%

    No Known Activations