© 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. 15612
    Prev
    Next
    INDEX
    Explanations

    stating options or model name

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

    This neuron detects floating‐point numeric values (decimal 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
     schade
    0.87
     incluido
    0.83
     требо
    0.83
     дли
    0.81
     cercanos
    0.80
     conocidos
    0.80
    
    0.79
     profesionales
    0.78
     vendidos
    0.78
    有限公司
    0.78
    POSITIVE LOGITS
    سع
    0.79
     Afterward
    0.73
     begins
    0.73
    กิน
    0.73
    ক
    0.73
    ষ
    0.71
     रा
    0.70
     허
    0.70
     mů
    0.70
    웰
    0.69
    Activations Density 0.000%

    No Known Activations