© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11079
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

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

    This neuron activates on numeric literals (numbers, including integers and floats) in the text.

    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_31_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
    )=(
    0.63
     синте
    0.63
     !,
    0.59
     দিবেন
    0.58
    )‏
    0.58
    திக்க
    0.57
    ]=(
    0.56
     бассей
    0.56
     jednej
    0.55
    Ϣ
    0.55
    POSITIVE LOGITS
    Time
    0.58
    Bye
    0.53
    time
    0.52
    because
    0.51
    TIME
    0.51
    ALTH
    0.51
    Health
    0.50
    หา
    0.49
    Turn
    0.49
    health
    0.48
    Activations Density 0.001%

    No Known Activations