© 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. 24-GEMMASCOPE-2-RES-16K
    7. 808
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens that are part of named entities—proper nouns, titles, and acronyms.

    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
     и
    0.62
     decrement
    0.55
    żeli
    0.53
     ও
    0.53
     ово
    0.53
     orbifold
    0.52
     و
    0.52
     ти
    0.52
     και
    0.52
     FeCl
    0.52
    POSITIVE LOGITS
    ™
    0.55
     extraordinaire
    0.53
     philanthropist
    0.51
    Other
    0.50
    Victoria
    0.50
    Pierre
    0.49
    的其他
    0.48
    ’
    0.48
    ville
    0.48
    Ryan
    0.48
    Activations Density 2.319%

    No Known Activations