© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6070
    Prev
    Next
    INDEX
    Explanations

    life expectancy

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

    The neuron is strongly activated by floating-point numeric tokens (numbers containing a decimal point).

    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
    께서
    0.89
    дного
    0.86
     cervix
    0.85
     CERN
    0.84
     Boynton
    0.82
     bienvenidos
    0.79
    т
    0.77
     Loyola
    0.76
     CTCF
    0.75
     tratar
    0.75
    POSITIVE LOGITS
    ↵
    0.88
    nosť
    0.73
     môžu
    0.66
     będą
    0.63
     দুর
    0.62
     fokus
    0.62
     பார்த்து
    0.61
    ักษณะ
    0.61
     ઉપર
    0.61
    begin
    0.59
    Activations Density 0.000%

    No Known Activations