© 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. 110932
    Prev
    Next
    INDEX
    Explanations

    float, inline, block

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

    This neuron fires on CSS stylesheet syntax, in particular CSS rule blocks and property names (e.g., the “{”, “clear”, “float”, “display” 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
     angst
    -0.77
     gerais
    -0.77
     revamp
    -0.77
     colspan
    -0.76
     overworked
    -0.71
    壺
    -0.71
    arov
    -0.70
     móviles
    -0.70
     oublier
    -0.70
    courseId
    -0.70
    POSITIVE LOGITS
     float
    2.47
    float
    2.36
     floated
    2.16
     floats
    2.11
     floating
    1.95
     Float
    1.84
    Float
    1.74
     FLOAT
    1.73
    FLOAT
    1.63
    floating
    1.63
    Activations Density 0.077%

    No Known Activations