© 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. 11260
    Prev
    Next
    INDEX
    Explanations

    shorter

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

    The neuron activates on tokens representing decimal numbers (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
    اگر
    0.74
     humanity
    0.73
    ্ধ্য
    0.72
     Wouldn
    0.71
     Humanity
    0.70
     j
    0.70
     étend
    0.69
    حية
    0.68
     August
    0.68
     Augustine
    0.68
    POSITIVE LOGITS
     flavon
    0.96
    finance
    0.78
    VIA
    0.78
    COVER
    0.78
    ונה
    0.77
    ท์
    0.77
    ి
    0.76
    carriage
    0.75
    SUB
    0.74
    SON
    0.74
    Activations Density 0.001%

    No Known Activations