© 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. 6308
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on capitalized tokens—especially proper names or organization titles.

    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
    ou
    0.79
    o
    0.71
    jenigen
    0.70
    relating
    0.70
     etti
    0.67
    шо
    0.64
    allenges
    0.64
    rows
    0.63
    gerald
    0.63
     ו
    0.63
    POSITIVE LOGITS
     cheaply
    0.82
     Skyrim
    0.82
     Tripura
    0.78
     catered
    0.77
    ИС
    0.77
     Highlander
    0.77
    பின்
    0.75
     SRS
    0.75
     CentOS
    0.74
    Tables
    0.74
    Activations Density 0.088%

    No Known Activations