© 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. 588
    Prev
    Next
    INDEX
    Explanations

    providing or using

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

    The neuron fires on non-English, non-ASCII tokens (especially Polish or Cyrillic words).

    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
     बेटियों
    0.50
    闓
    0.48
     noires
    0.47
    izophren
    0.47
    闿
    0.46
    ínas
    0.43
     prenez
    0.43
    nemonic
    0.43
     Shouldn
    0.43
    ឡិចត្រូ
    0.42
    POSITIVE LOGITS
    하는
    0.40
      
    0.39
    ieren
    0.38
          
    0.37
     kom
    0.36
     i
    0.36
     a
    0.35
     "
    0.35
     \"
    0.35
    ించిన
    0.35
    Activations Density 0.022%

    No Known Activations