© 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. 16361
    Prev
    Next
    INDEX
    Explanations

    single directory

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

    The neuron is primarily activated by numeric tokens representing decimal (floating-point) values.

    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
    Estos
    0.84
    Produto
    0.83
    Questo
    0.83
     punctato
    0.80
    Producto
    0.79
    Proble
    0.79
    כ
    0.78
    ج
    0.76
    lä
    0.76
    וכ
    0.76
    POSITIVE LOGITS
     Olivia
    0.79
     iler
    0.77
     Daff
    0.77
     Giants
    0.76
     Chichester
    0.76
     Cybersecurity
    0.76
     Szym
    0.75
     Miy
    0.74
     Cly
    0.73
     riparian
    0.73
    Activations Density 0.000%

    No Known Activations