© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7124
    Prev
    Next
    INDEX
    Explanations

    exploit, abuse, or endanger

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

    The neuron is primarily activated by numeric tokens and quantitative data (e.g. measurements, timestamps, file sizes, phone numbers, counts).

    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
    :
    0.93
    ,
    0.92
    .
    0.87
    '
    0.69
    í
    0.69
    at
    0.67
    TING
    0.66
    )
    0.64
    ः
    0.62
     >
    0.61
    POSITIVE LOGITS
     czyli
    1.16
     takže
    1.08
     który
    1.03
     INCLUDING
    1.00
     اتارنا
    1.00
     jossa
    0.99
     včetně
    0.99
     einschließlich
    0.95
     illetve
    0.93
     jonka
    0.91
    Activations Density 0.179%

    No Known Activations