© 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. 76021
    Prev
    Next
    INDEX
    Explanations

    speaker name before colon

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

    The neuron primarily fires on numeric tokens—especially time‐stamp markers and other standalone numbers in transcripts.

    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
    BEAN
    -1.00
     Cependant
    -0.97
    remacy
    -0.89
    ANTS
    -0.89
     Bean
    -0.88
    така
    -0.88
     medy
    -0.87
    您可以
    -0.87
     oma
    -0.87
    validated
    -0.86
    POSITIVE LOGITS
     ♪
    1.52
     [
    1.48
     narrator
    1.30
     announcer
    1.22
     NARR
    1.16
    Narrator
    1.16
     (
    1.15
    ♪
    1.09
    NARR
    1.05
     Narr
    1.04
    Activations Density 0.015%

    No Known Activations