© 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. 117389
    Prev
    Next
    INDEX
    Explanations

    television channels and media

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

    The neuron activates most strongly on mentions of television networks, channels, and other media/entertainment brand 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
     생
    -0.80
     เท
    -0.77
    Nhi
    -0.75
     Tada
    -0.75
    cbb
    -0.72
     inusual
    -0.71
     disgraced
    -0.70
    ៖
    -0.70
    lactin
    -0.69
    ipto
    -0.69
    POSITIVE LOGITS
     channel
    1.19
     channels
    1.16
     English
    0.98
     fta
    0.95
    english
    0.90
    getChannel
    0.90
    English
    0.89
    channels
    0.85
     ENGLISH
    0.84
    channel
    0.83
    Activations Density 0.023%

    No Known Activations