© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12340
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    This neuron activates on explicit temporal references, especially day names and other time‐of‐day expressions.

    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
     человеком
    0.94
    不久
    0.94
     sovi
    0.93
     человеку
    0.91
    并
    0.88
    प्टेंबर
    0.86
     avanc
    0.86
    Desired
    0.84
    埗
    0.83
    嗳
    0.83
    POSITIVE LOGITS
    ism
    1.13
    land
    0.89
     pomeriggio
    0.87
    дні
    0.87
    in
    0.86
    up
    0.85
    ya
    0.84
    ıl
    0.84
    ś
    0.83
    iverse
    0.83
    Activations Density 0.067%

    No Known Activations