© 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. 8920
    Prev
    Next
    INDEX
    Explanations

    last two Fibonacci numbers

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

    The neuron fires on words that immediately follow a precise decimal (floating-point) number.

    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
     لت
    0.87
     sinon
    0.87
     lomba
    0.79
    Пі
    0.79
     Hd
    0.78
     assurer
    0.77
     ناح
    0.77
    🍵
    0.77
     sovi
    0.76
    tea
    0.75
    POSITIVE LOGITS
    ла
    0.78
    ್ಯ
    0.77
    ли
    0.76
    AUS
    0.76
    REY
    0.76
    CEEDINGS
    0.76
    aan
    0.73
    RE
    0.72
    un
    0.70
    ANO
    0.70
    Activations Density 0.001%

    No Known Activations