© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4788
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is pick out dynamic action verbs (especially movement or process–oriented verbs).

    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
    .
    1.05
    _
    0.89
    ’
    0.87
    ı
    0.81
    '
    0.80
     deoarece
    0.71
    -
    0.68
    Ã
    0.68
    3
    0.66
    у
    0.66
    POSITIVE LOGITS
    ্পনিক
    0.88
     Persona
    0.76
    ধানা
    0.74
     Prendre
    0.73
    ध्यात्म
    0.73
    FlashValue
    0.72
     AirPods
    0.71
     minimalism
    0.71
     Moderna
    0.70
     attire
    0.69
    Activations Density 0.000%

    No Known Activations