© 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. 34-GEMMASCOPE-RES-131K
    7. 1239
    Prev
    Next
    INDEX
    Explanations

    radio and tv programs

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

    This neuron fires on tokens that are part of named entities in media contexts—especially the titles of radio shows, stations, or other branded program 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_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
    𝖕
    -0.74
     Krieges
    -0.73
     поту
    -0.73
    noi
    -0.71
     sufre
    -0.70
     дешевле
    -0.69
     Zwiebel
    -0.68
     parable
    -0.68
    Pew
    -0.68
     Text
    -0.68
    POSITIVE LOGITS
     weekday
    0.94
     programs
    0.94
     programas
    0.92
     Heard
    0.91
     program
    0.91
     levante
    0.90
     grises
    0.90
     weekly
    0.89
     برنامج
    0.89
     drive
    0.88
    Activations Density 0.042%

    No Known Activations