© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116058
    Prev
    Next
    INDEX
    Explanations

    audiobook narration performance

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

    The neuron is keyed to tokens representing numeric information—digits, durations, volumes, counts, and similar numerical details.

    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
     songwriting
    -0.85
     Fact
    -0.80
     anter
    -0.80
     questionnaire
    -0.77
     indoc
    -0.76
    連載
    -0.75
     vertical
    -0.74
     Vertical
    -0.71
    escens
    -0.71
     magazine
    -0.70
    POSITIVE LOGITS
     listeners
    1.83
     narrator
    1.62
    Listeners
    1.57
     listener
    1.57
     narration
    1.47
     Listener
    1.45
     Audible
    1.44
     listening
    1.41
    listeners
    1.36
     Listen
    1.30
    Activations Density 0.014%

    No Known Activations