© 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. 12079
    Prev
    Next
    INDEX
    Explanations

    code block endings

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

    The neuron detects tokens containing numeric values (i.e., digits or numbers embedded in code).

    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
     that
    0.57
     thats
    0.57
     or
    0.55
     him
    0.53
     mittler
    0.53
     (
    0.52
     esso
    0.52
     (!
    0.50
     Eiffel
    0.50
     essi
    0.50
    POSITIVE LOGITS
    𝗼
    0.52
    体验
    0.51
     była
    0.50
     همچنین
    0.49
    各项
    0.49
    уна
    0.48
    ллі
    0.48
    依赖
    0.48
    ун
    0.47
    是一种
    0.47
    Activations Density 0.006%

    No Known Activations