© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43259
    Prev
    Next
    INDEX
    Explanations

    mathematical or code symbols

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

    The neuron is primarily triggered by the asterisk character (“*”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     your
    -1.79
     of
    -1.78
    //
    -1.73
    e
    -1.66
     it
    -1.57
     contextLoads
    -1.48
     this
    -1.41
    ^{*}
    -1.41
    ys
    -1.39
    /*
    -1.38
    POSITIVE LOGITS
    </em>
    1.88
      
    1.63
    ꦶ
    1.48
                          
    1.43
    cadeau
    1.42
    Improved
    1.41
     ironic
    1.39
          
    1.39
    asının
    1.38
    damen
    1.37
    Activations Density 0.007%

    No Known Activations