© 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. 8650
    Prev
    Next
    INDEX
    Explanations

    Shared Universe

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

    The neuron strongly activates on standalone numeric values (especially decimals), such as timestamps or measurements.

    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
    ANA
    0.78
    ↵
    0.74
    3
    0.73
    NC
    0.73
    CHAR
    0.71
    UNG
    0.70
    5
    0.70
    4
    0.70
    IMA
    0.70
    ell
    0.69
    POSITIVE LOGITS
     камеры
    0.83
     попыта
    0.79
     конструкции
    0.78
     coffers
    0.77
     понрави
    0.76
     сумка
    0.76
    對方
    0.75
    mány
    0.74
     যথ
    0.73
     गायिका
    0.73
    Activations Density 0.001%

    No Known Activations