© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98757
    Prev
    Next
    INDEX
    Explanations

    voice qualities

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

    The neuron strongly activates on mentions of “voice,” effectively detecting when the text refers to a voice or voiceover.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     để
    -1.58
    昃
    -1.57
     blatantly
    -1.56
    ísticos
    -1.52
    磲
    -1.51
     what
    -1.50
     sizeable
    -1.50
     antiquated
    -1.49
    蛧
    -1.46
    ープン
    -1.45
    POSITIVE LOGITS
     again
    1.93
     previamente
    1.56
    缡
    1.55
     nimmer
    1.52
     anteriormente
    1.50
     was
    1.48
    給你
    1.46
     ihnen
    1.45
     praktisch
    1.45
    out
    1.44
    Activations Density 0.002%

    No Known Activations