© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58585
    Prev
    Next
    INDEX
    Explanations

    television stations and radio stations

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

    The neuron spotlights broadcast station call signs (i.e. all-caps letter sequences like “WHAM-TV,” “KCBS-TV,” “HF-DT,” etc.).

    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
    meneu
    -0.81
    韩国
    -0.79
    tened
    -0.77
     cambiare
    -0.75
     difíciles
    -0.74
    mycompany
    -0.74
     frecuente
    -0.74
    juego
    -0.73
    !==
    -0.73
     T
    -0.72
    POSITIVE LOGITS
     television
    1.01
     TV
    1.00
     radio
    1.00
    テレビ
    0.97
     tv
    0.91
     televisión
    0.90
    tv
    0.89
     televisiva
    0.88
     Channel
    0.87
     kanal
    0.87
    Activations Density 0.042%

    No Known Activations