© 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. 11120
    Prev
    Next
    INDEX
    Explanations

    computer policies

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

    The neuron activates on numeric tokens, especially decimal or large digit values, marking when a number or measurement appears.

    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
    stoffen
    0.80
     transitive
    0.76
     տ
    0.75
     lineWidth
    0.75
    льбе
    0.73
    ра
    0.72
     lineages
    0.70
     coordinate
    0.70
    ри
    0.69
    ल
    0.68
    POSITIVE LOGITS
     ET
    0.75
    čna
    0.71
     hadiah
    0.71
    像
    0.71
    aal
    0.71
     jad
    0.71
    션
    0.70
     LEAD
    0.70
     AMAZING
    0.70
    没
    0.70
    Activations Density 0.000%

    No Known Activations