© 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. 118153
    Prev
    Next
    INDEX
    Explanations

    key tags followed by punctuation or names

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

    The neuron identifies HTML/XML markup tokens (tag names, attributes, and their values).

    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
     .)
    -0.77
     incluso
    -0.75
    nico
    -0.75
     kooper
    -0.73
    Kino
    -0.72
     entiende
    -0.71
    rami
    -0.69
    वर
    -0.69
     commerciaux
    -0.69
    чник
    -0.69
    POSITIVE LOGITS
     Pledge
    0.88
    álního
    0.81
     Statements
    0.79
     prototypes
    0.78
    フライ
    0.78
     потім
    0.77
    tslib
    0.77
    攵
    0.75
     Gestaltung
    0.75
    titudine
    0.75
    Activations Density 0.020%

    No Known Activations