© 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. 16293
    Prev
    Next
    INDEX
    Explanations

    difficulty, marketing, environments

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

    The neuron specifically detects floating‐point or decimal number tokens.

    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
    ك
    0.90
    t
    0.87
    т
    0.77
     Springs
    0.75
    τες
    0.75
    go
    0.74
    ga
    0.74
    body
    0.73
    co
    0.71
    b
    0.70
    POSITIVE LOGITS
    IIUM
    0.91
    Ingrese
    0.90
    atributo
    0.88
     annak
    0.82
    Projeto
    0.81
    Estoy
    0.81
    ÑO
    0.80
    Enviar
    0.80
    Otra
    0.79
     actualización
    0.79
    Activations Density 0.000%

    No Known Activations