© 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. 5989
    Prev
    Next
    INDEX
    Explanations

    content, maid, picture, race, sick

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

    This neuron detects numeric expressions with decimal points (e.g., floating-point numbers in citations, measurements, or prices).

    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
    まるで
    0.73
     PLANTS
    0.68
     weltweit
    0.65
     環
    0.64
     อะไร
    0.63
     উদ্ভি
    0.62
     患者
    0.61
     TREATMENT
    0.61
     LANGUAGES
    0.61
     pembang
    0.60
    POSITIVE LOGITS
    に追加
    0.70
    /
    0.67
     revenir
    0.66
    \/
    0.64
     Schmitz
    0.63
     shirtless
    0.63
    刚才
    0.62
     this
    0.61
     boa
    0.61
     Wendell
    0.61
    Activations Density 0.133%

    No Known Activations