© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3279
    Prev
    Next
    INDEX
    Explanations

    python script execution

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

    The neuron strongly activates on programming‐related tokens—keywords, function/command names, and other code identifiers.

    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
    tanh
    0.63
    어도
    0.60
    உ
    0.60
    디
    0.59
    Также
    0.58
    ଧ
    0.58
    ఉ
    0.56
    Pup
    0.56
    undefined
    0.55
    יש
    0.55
    POSITIVE LOGITS
     @_
    0.86
    (@
    0.78
     "#{@
    0.75
     "#{
    0.74
    ("#{
    0.73
    ($_
    0.71
     ARTHUR
    0.70
     @
    0.70
     do
    0.68
     (@
    0.67
    Activations Density 0.026%

    No Known Activations