© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9051
    Prev
    Next
    INDEX
    Explanations

    time and time zones

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

    This neuron fires on tokens that make up time‐of‐day stamps (e.g. numeric hour/minute values and their “am”/“pm” markers).

    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
    ά
    0.63
    вар
    0.59
     বিশ্বাসের
    0.57
     hairy
    0.56
     माफिया
    0.56
    облада
    0.56
    ڡ
    0.56
    imately
    0.55
    uffs
    0.55
    getTarget
    0.55
    POSITIVE LOGITS
    )>=
    0.76
     แบ่ง
    0.71
    UMA
    0.69
     Municipal
    0.68
    Municipal
    0.68
    норий
    0.68
    సీ
    0.67
     அரசியல்
    0.67
     odk
    0.66
     Política
    0.66
    Activations Density 0.020%

    No Known Activations