© 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. 11049
    Prev
    Next
    INDEX
    Explanations

    dependency array

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

    The neuron strongly activates on numeric tokens—especially floating‐point numbers with decimal points.

    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
    tak
    0.98
    u
    0.97
    ó
    0.95
    paging
    0.89
    ем
    0.88
    ции
    0.87
    aktiv
    0.86
    рын
    0.84
    ister
    0.84
    atomy
    0.82
    POSITIVE LOGITS
     corruption
    0.81
    溁
    0.77
    それ
    0.77
     diverse
    0.75
     ブラウン
    0.74
     電力
    0.74
     ボディ
    0.74
     deeply
    0.73
     gigantic
    0.73
     necessitate
    0.72
    Activations Density 0.001%

    No Known Activations