© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2837
    Prev
    Next
    INDEX
    Explanations

    dates with months

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

    The neuron detects calendar dates, specifically month names paired with numeric day or year values.

    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
    ujem
    0.39
    ถ้า
    0.37
    😓
    0.36
    إذا
    0.36
    বয়
    0.35
    ровал
    0.35
    strcmp
    0.34
    новения
    0.34
    string
    0.34
    😞
    0.34
    POSITIVE LOGITS
     १९
    0.43
     ARTS
    0.39
     Parks
    0.39
     COLLE
    0.39
     unpublished
    0.38
     PRESS
    0.37
     BAY
    0.36
     FY
    0.36
     NEWS
    0.36
     partnering
    0.36
    Activations Density 0.060%

    No Known Activations