© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30506
    Prev
    Next
    INDEX
    Explanations

    font and color styling

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

    The neuron consistently spikes on the literal token “Font,” i.e. it’s detecting occurrences of the word “Font” (especially in code).

    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
     large
    -1.06
     considerable
    -0.83
     through
    -0.82
    restle
    -0.82
     during
    -0.81
    子は
    -0.80
    Компания
    -0.79
     sizable
    -0.79
     on
    -0.78
     what
    -0.78
    POSITIVE LOGITS
    FontStyle
    1.17
     FOUR
    0.93
     italic
    0.92
     aument
    0.91
    Tils
    0.91
     cumbre
    0.91
     SPECIAL
    0.89
    יתה
    0.89
     schar
    0.86
     INDEPENDENT
    0.85
    Activations Density 0.000%

    No Known Activations