© 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. 13202
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on brand, product, and company names (proper nouns identifying specific entities).

    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
    Ils
    0.59
    𒌋
    0.57
    賚
    0.57
     ませ
    0.55
    ufthansa
    0.55
    agir
    0.55
    Waterfall
    0.54
     truckers
    0.54
    VERTISE
    0.53
    Extract
    0.53
    POSITIVE LOGITS
     scooter
    1.52
     scooters
    1.43
     Scooter
    1.30
     स्कूटर
    1.30
     tricycle
    1.15
     ATV
    1.13
     riding
    1.10
     ridden
    1.09
    🛴
    1.09
     scoot
    1.09
    Activations Density 0.364%

    No Known Activations