© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10523
    Prev
    Next
    INDEX
    Explanations

    make sure

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

    This neuron activates on tokens containing the character sequence “mak” (in any case), such as in names like Makawao, Maksimov, Yakutia, “MAKE,” “make‐up,” or Wagemaker.

    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
    翊
    0.59
     moor
    0.58
    ockeys
    0.55
    iffen
    0.53
     provocation
    0.52
    <0xD2>
    0.51
    লিক
    0.50
    <0xC7>
    0.50
    ща
    0.50
    ifs
    0.48
    POSITIVE LOGITS
     sure
    0.83
     sû
    0.67
     SURE
    0.67
     olds
    0.59
     intitulé
    0.59
    enzie
    0.58
    確
    0.58
     makin
    0.58
     esemplari
    0.57
    ⛩
    0.57
    Activations Density 0.143%

    No Known Activations