© 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. 9843
    Prev
    Next
    INDEX
    Explanations

    event

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

    The neuron responds strongly to capitalized tokens beginning with the letters “Ev.”

    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
     igu
    0.67
     decimos
    0.62
     jeopardy
    0.60
     accidental
    0.59
     opener
    0.58
     endorsement
    0.58
     examiner
    0.58
    📩
    0.57
     exemption
    0.57
     Igu
    0.57
    POSITIVE LOGITS
    geny
    0.77
    uates
    0.76
    horizon
    0.75
    Ev
    0.74
     Ev
    0.72
    uality
    0.72
     ev
    0.70
    क्रम
    0.70
    distant
    0.69
    brite
    0.68
    Activations Density 0.170%

    No Known Activations