© 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. 10271
    Prev
    Next
    INDEX
    Explanations

    learning reinforcement learning

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on relatively uncommon, content-bearing nouns or specialized terms (especially proper names and domain-specific vocabulary).

    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
    Aloe
    0.64
     قدیمی
    0.64
    ༞
    0.63
    ogyakarta
    0.63
     совершенно
    0.63
     อื่น
    0.62
     Несмотря
    0.62
    就不会
    0.61
    ◕
    0.61
     الأخرى
    0.61
    POSITIVE LOGITS
     impactful
    0.78
     matchups
    0.73
     matchup
    0.71
     FanDuel
    0.69
     awards
    0.68
     deliverables
    0.68
     metrics
    0.66
     portion
    0.64
     filets
    0.64
     postseason
    0.64
    Activations Density 0.089%

    No Known Activations