© 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. 11853
    Prev
    Next
    INDEX
    Explanations

    loop structures and code examples

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

    The neuron detects numeric tokens, i.e. standalone digits or multi‐digit 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
    ೆಯ
    0.32
    Liu
    0.31
     degraded
    0.30
    ad
    0.30
     two
    0.30
     usual
    0.29
    ێکی
    0.29
    Ė
    0.29
     అలా
    0.29
    Ě
    0.29
    POSITIVE LOGITS
    promises
    0.38
     bolsas
    0.37
     legislación
    0.36
     пути
    0.35
     કે
    0.34
     experiencias
    0.34
     ।
    0.34
     جرام
    0.34
     instrumentos
    0.33
     guidelines
    0.33
    Activations Density 0.000%

    No Known Activations