© 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. 7882
    Prev
    Next
    INDEX
    Explanations

    python scripts

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

    The neuron activates on numeric tokens—especially version numbers, counts, floats, and other digit‐based 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_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
    mouseleave
    0.74
     исход
    0.62
     tatha
    0.61
    става
    0.57
    포
    0.54
     uint
    0.53
     hee
    0.52
     तब्
    0.52
     przest
    0.50
     잘못
    0.50
    POSITIVE LOGITS
     Author
    0.69
     Import
    0.66
    Author
    0.66
    Import
    0.66
     ImportError
    0.65
    #!/
    0.65
    from
    0.61
     author
    0.58
    #!
    0.58
     penulis
    0.58
    Activations Density 0.003%

    No Known Activations