© 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. 31-GEMMASCOPE-2-RES-16K
    7. 590
    Prev
    Next
    INDEX
    Explanations

    information about him

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

    The neuron primarily detects numeric expressions (i.e. tokens representing numbers or quantities).

    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_31_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
     그리고
    0.50
    そして
    0.46
     і
    0.46
    1
    0.45
     そして
    0.45
     এরা
    0.44
    2
    0.44
     따라서
    0.44
     according
    0.44
    0
    0.43
    POSITIVE LOGITS
     how
    1.09
     why
    0.97
     bagaimana
    0.93
     nasıl
    0.88
    如何
    0.87
     hvordan
    0.87
     whether
    0.84
     কিভাবে
    0.82
     cómo
    0.81
     كيفية
    0.81
    Activations Density 0.714%

    No Known Activations