© 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. 90226
    Prev
    Next
    INDEX
    Explanations

    code block closing tags

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

    The neuron fires on code- or markup-style identifiers and metadata tokens (e.g. tag names, frontmatter field names, header-guard macros).

    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
    ůj
    -0.69
     objections
    -0.68
    了过来
    -0.65
     Зо
    -0.65
    확
    -0.65
     Master
    -0.64
     Chit
    -0.63
    terr
    -0.63
    drawn
    -0.62
     پای
    -0.62
    POSITIVE LOGITS
    聘
    0.71
     крепления
    0.69
     interaction
    0.69
    Interaction
    0.69
    interaction
    0.67
     Hyperion
    0.67
     Inoue
    0.66
     Zombie
    0.66
    lyse
    0.66
     listed
    0.66
    Activations Density 0.045%

    No Known Activations