© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12377
    Prev
    Next
    INDEX
    Explanations

    screens, especially for displays or cameras

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

    The neuron strongly activates for mentions of video-display or entertainment equipment (e.g. TV, DVD, screens, projectors, audio-visual devices).

    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_24_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
    &
    0.65
    лось
    0.61
    +
    0.61
    (
    0.58
    vers
    0.56
    1
    0.56
    aine
    0.55
    mid
    0.54
    ject
    0.53
    꽁
    0.52
    POSITIVE LOGITS
     terutama
    0.89
     radiotherapy
    0.80
     movieId
    0.79
     pecinta
    0.77
     especialmente
    0.77
     cinema
    0.73
     movieList
    0.73
     щоб
    0.72
     সিনেমা
    0.72
     وید
    0.72
    Activations Density 0.047%

    No Known Activations