© 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. 64537
    Prev
    Next
    INDEX
    Explanations

    podcast listener sponsor

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

    The neuron fires on promotional or sponsorship disclosure text, especially segments containing prices, numeric offers, and coupon or affiliate codes.

    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
     reutiliz
    -0.81
     other
    -0.73
    虽说
    -0.72
     differing
    -0.71
     tū
    -0.70
     Estamos
    -0.70
    jalá
    -0.69
    دل
    -0.68
    けどね
    -0.67
    轻易
    -0.67
    POSITIVE LOGITS
     listeners
    1.77
     listener
    1.49
    Listeners
    1.34
     Listener
    1.22
    listeners
    1.22
    Listener
    1.15
    listener
    1.13
     sponsor
    1.13
    ChangeListener
    1.03
    sponsor
    0.95
    Activations Density 0.014%

    No Known Activations