© 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. 14098
    Prev
    Next
    INDEX
    Explanations

    list items or code structure

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

    The neuron activates on 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
    או
    0.88
    دي
    0.82
    ক্টো
    0.82
     insistent
    0.79
    স
    0.79
    дат
    0.78
    га
    0.76
    𝐜
    0.75
     Edinburgh
    0.75
    ђено
    0.75
    POSITIVE LOGITS
    talk
    0.79
     jis
    0.75
     dichos
    0.75
    ar
    0.73
     tamaños
    0.73
     impactos
    0.73
     ilus
    0.72
     artık
    0.70
    袢
    0.70
     ahora
    0.69
    Activations Density 0.000%

    No Known Activations