© 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. 10-GEMMASCOPE-RES-131K
    7. 13955
    Prev
    Next
    INDEX
    Explanations

    font names and styles

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

    The neuron detects occurrences of font names (and font-family specifications) in code or style 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_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
    bộ
    -1.38
     that
    -1.38
     Independiente
    -1.36
     holand
    -1.32
     ảnh
    -1.30
     Tarjeta
    -1.25
     voeten
    -1.23
     اندروید
    -1.20
    ֶּ
    -1.19
     گیری
    -1.18
    POSITIVE LOGITS
    LayoutStyle
    1.55
     AssemblyCompany
    1.36
     všechny
    1.31
    your
    1.30
    zondere
    1.29
    鋱
    1.24
    Біографія
    1.22
     mindestens
    1.21
     всі
    1.21
    those
    1.21
    Activations Density 0.027%

    No Known Activations