© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59840
    Prev
    Next
    INDEX
    Explanations

    font size and labels

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

    This neuron responds to code‐style identifiers and literals—things like parameter/attribute names (e.g. Font, xlabel, ylabel, label, NOTICE, JVM) and numeric tokens.

    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
    ponse
    -0.79
    olia
    -0.75
    瞠
    -0.74
    río
    -0.73
    stom
    -0.72
    riya
    -0.70
     commencent
    -0.70
    ixin
    -0.70
     ligand
    -0.69
    hene
    -0.69
    POSITIVE LOGITS
     fontsize
    1.13
     font
    1.05
    fontsize
    1.01
     Font
    0.96
    Interpreter
    0.94
     horizontal
    0.94
    Font
    0.93
     rotation
    0.86
     vertical
    0.84
    Horizontal
    0.84
    Activations Density 0.003%

    No Known Activations