© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6544
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to abstract noun forms, especially words ending in “-ity.”

    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
    characters
    0.77
     abilities
    0.70
    comers
    0.66
    飛び
    0.65
    骼
    0.63
     способности
    0.63
    ם
    0.62
     possibilities
    0.61
    이나
    0.61
    ্বক
    0.61
    POSITIVE LOGITS
    yyyyyyyy
    0.84
    ты
    0.69
    งาม
    0.67
     densidad
    0.66
    低い
    0.65
    يي
    0.64
    の高い
    0.64
    t
    0.63
    yyyy
    0.62
    riek
    0.61
    Activations Density 0.500%

    No Known Activations