© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7471
    Prev
    Next
    INDEX
    Explanations

    dates and ranges

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

    The neuron specializes in spotting explicit date and time expressions (e.g., years, months, and day numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phrases indicating when a law, rule, or regulation takes effect or becomes enforceable.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of laws or rules taking effect, including formal effective dates and timelines with specific calendar dates.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    രുവനന്തപു
    0.59
    ഹി
    0.55
    queta
    0.53
    неш
    0.52
    untamento
    0.52
     совместно
    0.51
    を開催
    0.51
    dSample
    0.50
     finito
    0.50
    წინ
    0.50
    POSITIVE LOGITS
     effective
    1.23
    Effective
    1.19
     Effective
    1.17
     mulai
    1.16
     January
    1.16
     beginning
    1.15
    effective
    1.13
    January
    1.11
    生效
    1.10
    beginning
    1.09
    Activations Density 0.296%

    No Known Activations