© 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. 14049
    Prev
    Next
    INDEX
    Explanations

    Azure services

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

    The neuron activates on numeric tokens (particularly decimal numbers), flagging numerical values in the text.

    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
    歴
    0.75
     nationals
    0.72
     soweit
    0.72
     отзывы
    0.71
    在一
    0.71
     Freshman
    0.70
     جميع
    0.70
    AtIndex
    0.69
    íř
    0.69
    iges
    0.67
    POSITIVE LOGITS
    et
    0.80
    कान
    0.80
    jing
    0.80
    th
    0.78
    듈
    0.75
    crystall
    0.75
    장
    0.74
    as
    0.73
    m
    0.72
    DO
    0.72
    Activations Density 0.000%

    No Known Activations