© 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. 12749
    Prev
    Next
    INDEX
    Explanations

    now

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

    The neuron fires on expressions of quantified amounts or counts (e.g. “a new record,” “about five pounds,” “a bunch of students,” “a lot of book boxes”).

    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
     galima
    0.95
    ین
    0.89
    ج
    0.84
     autrefois
    0.84
    ساز
    0.79
     anteriormente
    0.78
    不仅
    0.77
    するため
    0.75
    になると
    0.75
    ن
    0.75
    POSITIVE LOGITS
     сейчас
    1.63
     now
    1.51
     currently
    1.38
     এখন
    1.37
    currently
    1.34
     сега
    1.30
    現在
    1.25
     atualmente
    1.25
     ahora
    1.24
     دلوقتي
    1.23
    Activations Density 1.335%

    No Known Activations