© 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. 7573
    Prev
    Next
    INDEX
    Explanations

    past seasons and years

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

    This neuron detects numeric tokens representing quantitative statistics or measurements (e.g., multi‐digit numbers for years, seasons, scores, and other numerical data).

    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
     MONTH
    0.66
    지
    0.66
     週
    0.61
     కొత్త
    0.61
    ACTION
    0.61
     새로운
    0.61
    今天要
    0.60
     月
    0.59
     MIT
    0.59
     NOT
    0.59
    POSITIVE LOGITS
     Campeonato
    0.86
     stints
    0.86
     aastal
    0.79
    ʋ
    0.79
    땐
    0.77
    ylsulfanyl
    0.74
    éries
    0.74
    aided
    0.72
    ɤ
    0.72
     జట్టు
    0.71
    Activations Density 0.059%

    No Known Activations