© 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. 10316
    Prev
    Next
    INDEX
    Explanations

    drag and drop actions

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

    The neuron strongly activates on words that signal temporal context (e.g. past‐ or present‐time markers like “Wrote,” “present,” “current”).

    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
    ’
    0.84
    ,
    0.79
     ngang
    0.76
     proxim
    0.73
     και
    0.73
     ו
    0.73
     owe
    0.73
    ،
    0.72
     envol
    0.71
     zvlá
    0.70
    POSITIVE LOGITS
     Obwohl
    0.86
     remittances
    0.82
    tcpHeader
    0.82
    來越
    0.82
     Somit
    0.81
     signboard
    0.79
    晉
    0.78
    गोलिक
    0.77
    Translatef
    0.76
    Após
    0.76
    Activations Density 0.001%

    No Known Activations