© 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. 5514
    Prev
    Next
    INDEX
    Explanations

    The neuron consistently activates on numeric tokens with decimal points (floating-point numbers).

    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
    ۶
    0.78
     acclaim
    0.77
     Prolong
    0.77
    ۸
    0.75
    ڈی
    0.74
     spirited
    0.73
     PROM
    0.73
    ورہ
    0.73
     scorched
    0.73
     perme
    0.73
    POSITIVE LOGITS
    carlo
    0.83
    нка
    0.75
    anze
    0.75
    ーズ
    0.71
    꿍
    0.70
    ordum
    0.69
    electron
    0.68
    aqueous
    0.68
    featur
    0.68
    erei
    0.67
    Activations Density 0.000%

    No Known Activations