© 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. 10675
    Prev
    Next
    INDEX
    Explanations

    migrating everything at once

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

    The neuron strongly activates on floating-point numeric tokens (numbers containing a decimal point).

    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
    ק
    0.82
    做
    0.82
    Hej
    0.75
    我
    0.73
    五
    0.73
    อ
    0.72
    个
    0.71
         
    0.71
    полу
    0.70
    呵呵
    0.70
    POSITIVE LOGITS
    لة
    0.85
     tabel
    0.84
     गर्भावस्था
    0.84
     dargestellt
    0.84
     যদিও
    0.81
    -\
    0.80
     promulg
    0.79
     کہانی
    0.79
    ^{(\
    0.79
     longitud
    0.79
    Activations Density 0.000%

    No Known Activations