© 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. 10662
    Prev
    Next
    INDEX
    Explanations

    section structure, reporting, analysis

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

    This neuron fires on numeric tokens—particularly decimal numbers and other numeric measurements.

    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
    ных
    0.87
    ренных
    0.86
    ta
    0.78
    daten
    0.76
     Phy
    0.76
     vgl
    0.74
    ]]
    0.73
    f
    0.73
    lly
    0.73
     Establishing
    0.73
    POSITIVE LOGITS
     недоста
    0.79
     ornaments
    0.76
     შესაძ
    0.70
     ornamental
    0.69
     ornament
    0.68
     escultura
    0.68
     biscuit
    0.68
     decorated
    0.68
     пожела
    0.67
     decoded
    0.66
    Activations Density 0.000%

    No Known Activations