© 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. 4444
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for terms that name or describe organized activities, events, or projects.

    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
    ávání
    0.81
     enterprising
    0.79
     hapless
    0.74
     resourceful
    0.74
     จํา
    0.69
    বিভিন্ন
    0.69
    ሟ
    0.69
    などが
    0.68
     pandemics
    0.67
    HashSet
    0.66
    POSITIVE LOGITS
     itself
    1.01
    e
    0.90
    as
    0.86
     was
    0.85
     був
    0.84
     повністю
    0.80
    er
    0.79
     ήταν
    0.77
    maker
    0.77
     இல்லை
    0.76
    Activations Density 2.479%

    No Known Activations