© 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. 8811
    Prev
    Next
    INDEX
    Explanations

    differentiated product

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

    The neuron is tuned to detect floating-point numbers (numerical tokens containing decimal points).

    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
     ସ
    0.83
     մ
    0.79
     ﺍﻟ
    0.79
     சூரிய
    0.77
     실행
    0.77
     אני
    0.76
     দ্বি
    0.75
     practicable
    0.75
     directly
    0.74
     ఉ
    0.74
    POSITIVE LOGITS
    اب
    0.80
    ரும
    0.76
     nogle
    0.75
    राणिक
    0.73
     partager
    0.73
    Cet
    0.72
     débit
    0.72
     било
    0.71
    keiten
    0.69
    न्देल
    0.68
    Activations Density 0.003%

    No Known Activations