© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86047
    Prev
    Next
    INDEX
    Explanations

    audio engineer, producer, mixer

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

    The neuron is spotting technical audio-production terms and names—particularly plugin/software/tool names (often with version numbers) and audio-engineering roles.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     bailando
    -1.23
    されていました
    -1.21
     hectáreas
    -1.20
    一段时间
    -1.20
     которых
    -1.20
     olhando
    -1.16
     cuyo
    -1.16
    “
    -1.16
     cansado
    -1.15
     mirando
    -1.13
    POSITIVE LOGITS
    QUÉ
    1.38
     veste
    1.30
    áneamente
    1.29
     to
    1.22
    峨
    1.18
    ziell
    1.15
    шный
    1.13
    𝕿
    1.13
     arranger
    1.13
     sente
    1.13
    Activations Density 0.047%

    No Known Activations