© 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. 7063
    Prev
    Next
    INDEX
    Explanations

    PDF.AddPage(Page)

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

    The neuron detects numeric tokens—especially decimal numbers, footnote-style markers, and other purely numeric or numeric-annotation tokens.

    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
    差异
    0.66
     marginalized
    0.63
    roveň
    0.63
     Choir
    0.61
     differences
    0.59
    差異
    0.59
    视
    0.59
    च्या
    0.58
    ளவில்
    0.58
    čiť
    0.57
    POSITIVE LOGITS
    Antes
    0.63
    年末
    0.59
    प्ल
    0.58
    ौली
    0.58
     Gleich
    0.57
    Luego
    0.55
    Fernando
    0.55
     الوا
    0.55
     ን
    0.55
    ad
    0.54
    Activations Density 0.237%

    No Known Activations