© 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. 12780
    Prev
    Next
    INDEX
    Explanations

    // and " parts" structure

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

    The neuron is overwhelmingly triggered by date/time and other numeric metadata (timestamps, upload dates, file dimensions, etc.) in the document.

    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
    ão
    0.83
    mm
    0.77
    g
    0.76
    άρ
    0.75
    ग्री
    0.75
    lé
    0.74
    эле
    0.73
    𝘧
    0.73
    nemen
    0.72
    στε
    0.71
    POSITIVE LOGITS
    리
    0.96
     APPE
    0.81
     definit
    0.77
    estima
    0.77
     CMO
    0.75
    나
    0.74
    ява
    0.73
     outcrop
    0.73
    ंपूर्
    0.72
     перебу
    0.72
    Activations Density 0.000%

    No Known Activations