© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16241
    Prev
    Next
    INDEX
    Explanations

    simplifies or provides this example

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

    This neuron lights up on the key words and numbers that appear in prescriptive or constraint‐setting sentences—i.e. the verbs, pronouns, and numerals used when stating instructions, requirements, or limits.

    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
    8
    0.71
    5
    0.68
    7
    0.66
    首先
    0.64
    which
    0.63
    最初に
    0.63
    because
    0.63
    4
    0.62
    만이
    0.60
    Наи
    0.60
    POSITIVE LOGITS
     cosplay
    0.87
     triathlon
    0.85
     infographics
    0.84
     Taehyung
    0.84
     photoshoot
    0.84
     infographic
    0.83
     coworking
    0.83
     multilateral
    0.83
     Coinbase
    0.82
     масштаб
    0.82
    Activations Density 0.003%

    No Known Activations