© 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. 5986
    Prev
    Next
    INDEX
    Explanations

    speech start tags

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

    This neuron primarily fires on structured data tokens—especially numbers (years, percentages, statistics) and technical 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
    J
    0.34
    Tol
    0.34
    voř
    0.31
    Wol
    0.31
    X
    0.31
    Auction
    0.31
    Magic
    0.31
    Phosph
    0.30
    F
    0.30
     الاتحاد
    0.30
    POSITIVE LOGITS
     massaging
    0.43
     scrolling
    0.42
     ergonomic
    0.38
     massages
    0.38
     ৩০০
    0.37
     peruse
    0.37
     categorize
    0.37
     memes
    0.36
     monday
    0.36
     spins
    0.36
    Activations Density 0.037%

    No Known Activations