© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 901
    Prev
    Next
    INDEX
    Explanations

    delimiters for code/data

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

    This neuron flags numerical tokens and numeric data (counts, percentages, decimal 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
    ’
    0.45
     roaming
    0.44
    र्मेंद्र
    0.42
    world
    0.42
     rendezvous
    0.41
     origami
    0.41
    spro
    0.41
    世界的
    0.41
     opérations
    0.40
    heads
    0.40
    POSITIVE LOGITS
     RetValue
    0.56
     ૩
    0.54
     たり
    0.54
    !।
    0.52
     ១
    0.51
    4
    0.51
     ۲
    0.50
     Beberapa
    0.50
     ૧
    0.50
    ﭜ
    0.49
    Activations Density 0.015%

    No Known Activations