© 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. 7783
    Prev
    Next
    INDEX
    Explanations

    nth, kth, ith index

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

    This neuron responds to technical terms for numeric data and data structures in programming contexts (e.g. “numbers,” “array,” “input,” “integers”).

    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
    ['
    0.79
    [:-
    0.71
    ["
    0.70
     ['
    0.70
    ['_
    0.67
    [:]
    0.66
     ["
    0.60
    ['-
    0.60
    [-
    0.59
    [::-
    0.58
    POSITIVE LOGITS
     nth
    1.22
    第
    1.16
     kth
    1.08
    nth
    1.01
    elementAt
    0.98
     第
    0.96
     ith
    0.95
    第九
    0.93
    第八
    0.88
     ninth
    0.87
    Activations Density 0.015%

    No Known Activations