© 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. 22-GEMMASCOPE-RES-131K
    7. 26269
    Prev
    Next
    INDEX
    Explanations

    voice actors and roles

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

    This neuron detects mentions of voice acting credits, such as “Voice Actor:” or “voiced by” and the associated actor names.

    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
     السياس
    -1.34
     $
    -1.31
     take
    -1.19
     assessment
    -1.17
     time
    -1.15
    の方法
    -1.08
     solucionar
    -1.07
     tlie
    -1.07
     ベクトル
    -1.06
    =$("#
    -1.06
    POSITIVE LOGITS
     voice
    1.70
     voices
    1.30
     plastiques
    1.29
    Personajes
    1.28
    ofing
    1.28
     suara
    1.27
     gela
    1.25
     acheter
    1.23
     chèvre
    1.22
     salade
    1.20
    Activations Density 0.013%

    No Known Activations