© 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. 34-GEMMASCOPE-RES-131K
    7. 49763
    Prev
    Next
    INDEX
    Explanations

    font-family sans-serif, copyright, slug

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

    The neuron consistently detects the appearance of the word “sans” (as in “sans-serif”) in font-family declarations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     left
    -0.73
     notch
    -0.71
    Hrsg
    -0.70
     Act
    -0.69
     박
    -0.69
    しかったです
    -0.68
     Liber
    -0.68
    azole
    -0.66
    lights
    -0.66
    aronder
    -0.66
    POSITIVE LOGITS
     FRANCIS
    0.75
    Mot
    0.70
     Receipt
    0.70
    mot
    0.69
     Bedienung
    0.69
     clos
    0.68
     salted
    0.67
    numeros
    0.67
    affaires
    0.67
     obligated
    0.67
    Activations Density 0.108%

    No Known Activations