© 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. 5633
    Prev
    Next
    INDEX
    Explanations

    structured list headings

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

    The neuron fires on standalone section headers or labeled advice markers (e.g. “Tip,” “Reason,” “This,” “Here’s”) that introduce new segments or numbered points.

    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
     unambiguous
    0.66
     syntactic
    0.59
     perturbative
    0.56
     oligonucleotide
    0.55
     hypergeometric
    0.52
     carboxylic
    0.52
    ǎ
    0.52
     நூற்றாண்டின்
    0.51
    テキスト
    0.51
    ナソニック
    0.51
    POSITIVE LOGITS
     a
    0.64
    ,
    0.64
    4
    0.59
    0
    0.54
    2
    0.54
    1
    0.53
    6
    0.53
    ව
    0.53
     ايضا
    0.52
    Fees
    0.52
    Activations Density 0.001%

    No Known Activations