© 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. 31-GEMMASCOPE-2-RES-16K
    7. 18
    Prev
    Next
    INDEX
    Explanations

    numbers and fractions

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

    The neuron is detecting floating-point numbers (decimal numerals) wrapped in parentheses.

    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_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
    বিষ্য
    0.46
    𒅌
    0.41
    environnement
    0.40
    añas
    0.40
    ብሰ
    0.40
    🕍
    0.39
    🏬
    0.39
    preneurs
    0.39
    intahan
    0.38
     ідэ
    0.38
    POSITIVE LOGITS
    7
    0.82
    6
    0.80
    8
    0.79
    5
    0.75
    3
    0.75
    4
    0.75
    9
    0.75
    0.74
     ৮
    0.63
     ३
    0.62
    Activations Density 1.200%

    No Known Activations