© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13283
    Prev
    Next
    INDEX
    Explanations

    analogous situations, location context, static descriptions

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

    This neuron detects floating‐point numeric values (numbers containing a decimal point).

    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
     หม
    0.73
     ライン
    0.66
     Machinist
    0.64
     subpar
    0.64
     MenuView
    0.64
     ด่า
    0.64
     욕
    0.63
     máquina
    0.62
    ERING
    0.62
     ecmaVersion
    0.62
    POSITIVE LOGITS
     acrescent
    0.73
    এছ
    0.73
    டன்
    0.71
    isations
    0.70
    ë
    0.70
    ised
    0.70
    ucidation
    0.70
     neighbouring
    0.69
    ضافة
    0.67
    可以说
    0.66
    Activations Density 0.004%

    No Known Activations