© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10438
    Prev
    Next
    INDEX
    Explanations

    TV shows or soap operas

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

    The neuron is tuned to detect mentions of the soap‐opera title “General Hospital” (especially in the context of spoilers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PoE
    0.66
     Minecraft
    0.66
     minecraft
    0.61
     Poe
    0.61
    Minecraft
    0.61
     casque
    0.59
    Helmet
    0.59
    ⌘
    0.59
    Spotify
    0.57
    ▐
    0.55
    POSITIVE LOGITS
     soap
    1.73
     soaps
    1.61
     Soap
    1.52
     soapy
    1.45
    soap
    1.38
    Soap
    1.35
     telenov
    1.30
     सीरियल
    1.09
     Daytime
    1.07
     SOAP
    1.05
    Activations Density 0.156%

    No Known Activations