© 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. 10409
    Prev
    Next
    INDEX
    Explanations

    x / X in equations

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

    This neuron detects numeric tokens or sequences—i.e. numbers (including multi‐digit, decimal, and numbered references).

    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
    Jacobi
    0.89
    (',')
    0.89
    ны
    0.86
    璘
    0.85
     encapsulate
    0.83
    罟
    0.82
    ucidation
    0.82
    Hector
    0.82
     Евгений
    0.82
     Ambris
    0.82
    POSITIVE LOGITS
     produtt
    0.96
     proprietà
    0.91
    0.88
     città
    0.86
    accia
    0.80
     realtà
    0.79
    š
    0.76
     più
    0.75
     miglior
    0.75
     quantità
    0.72
    Activations Density 0.000%

    No Known Activations