© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8539
    Prev
    Next
    INDEX
    Explanations

    knowledge base access

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

    This neuron activates on numeric tokens, especially floating-point numbers (e.g., decimal measurements or citation identifiers).

    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
    st
    0.83
    ut
    0.81
    nj
    0.80
    en
    0.78
    open
    0.77
    [](
    0.77
    yon
    0.77
    ww
    0.76
    “(
    0.75
    ++
    0.74
    POSITIVE LOGITS
    ស់
    0.81
     imgSrc
    0.80
     mLocation
    0.75
     vastu
    0.74
     photospheres
    0.74
     সব্ব
    0.73
     endophytic
    0.73
    त्रेयी
    0.73
     stdout
    0.72
     hekt
    0.72
    Activations Density 0.000%

    No Known Activations