© 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. 10240
    Prev
    Next
    INDEX
    Explanations

    month-year

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

    The neuron is triggered by numeric or quantitative tokens (e.g. page numbers, years, measurements, statistics).

    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
    time
    0.70
     Malam
    0.69
     Qualifying
    0.68
    0.68
     médio
    0.65
    pm
    0.64
    can
    0.63
    #,
    0.63
     Doe
    0.63
    POSITIVE LOGITS
    㝌
    0.86
     constitute
    0.84
     került
    0.84
    ৩
    0.83
    დნენ
    0.82
     scav
    0.82
     misled
    0.82
    ﺒ
    0.81
     умер
    0.79
     cathodes
    0.79
    Activations Density 0.000%

    No Known Activations