© 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. 4801
    Prev
    Next
    INDEX
    Explanations

    actions and outcomes

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

    The neuron detects numeric tokens containing decimal points (floating-point numbers).

    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
    ی
    0.88
    a
    0.82
    ej
    0.81
    اگر
    0.80
    eat
    0.79
    eau
    0.76
    oł
    0.76
    ece
    0.75
    ي
    0.75
    eep
    0.74
    POSITIVE LOGITS
     llamadas
    0.89
    様
    0.88
     vorm
    0.84
    に変
    0.81
     humanos
    0.79
     представлены
    0.79
     chamado
    0.79
     temel
    0.79
     estadounidense
    0.79
     llamados
    0.78
    Activations Density 0.000%

    No Known Activations