© 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. 59276
    Prev
    Next
    INDEX
    Explanations

    flex and flexible layout

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

    This neuron fires on HTML markup tokens, especially angle-bracketed tags and their id/class attributes.

    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
     наблюда
    -0.92
     STR
    -0.88
    Œ
    -0.76
     головой
    -0.75
    nici
    -0.75
    quoted
    -0.73
    #:
    -0.73
     cale
    -0.72
    licación
    -0.71
     Gens
    -0.71
    POSITIVE LOGITS
     FLEX
    1.20
     flex
    1.16
    flex
    1.11
    Flex
    1.05
    FLEX
    1.03
     Flex
    0.99
     flexing
    0.93
    ひ
    0.78
     flexible
    0.77
     Flexible
    0.77
    Activations Density 0.026%

    No Known Activations