© 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. 7441
    Prev
    Next
    INDEX
    Explanations

    operators and code symbols

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

    The neuron strongly activates on numeric constants (especially floating‐point numbers) and the arithmetic operators around them.

    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
    you
    0.77
     same
    0.75
     गड
    0.74
     côtés
    0.73
     गावात
    0.73
     }_{
    0.71
    ᑯ
    0.71
     तुमच्या
    0.71
    鈺
    0.70
     you
    0.69
    POSITIVE LOGITS
     admins
    0.88
     entrar
    0.84
    樵
    0.84
     ("/
    0.83
     intellig
    0.83
    🠀
    0.83
    PARTMENT
    0.82
    初の
    0.82
    ********/
    0.82
     promos
    0.81
    Activations Density 0.010%

    No Known Activations