© 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. 7780
    Prev
    Next
    INDEX
    Explanations

    extract/define types

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

    The neuron fires on auxiliary or modal expressions that convey ability, permission, or potential.

    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
    uz
    0.70
    з
    0.67
    sic
    0.66
    אל
    0.66
     mno
    0.64
     важли
    0.64
     рік
    0.64
    ♐
    0.63
    #!/
    0.63
    ו
    0.63
    POSITIVE LOGITS
     oferecer
    0.87
     Gérard
    0.85
     Bamber
    0.83
    ধর
    0.82
    GONDOR
    0.81
     Somerville
    0.81
     reduzir
    0.80
     Gonçalves
    0.80
     написать
    0.78
    সম্যান
    0.77
    Activations Density 0.000%

    No Known Activations