© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64999
    Prev
    Next
    INDEX
    Explanations

    PUBLIC DOCTYPE declarations

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

    The neuron strongly lights up on HTML/XML boilerplate and markup tokens (e.g. DOCTYPE, PUBLIC, html, meta, http-equiv, etc.).

    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
    avait
    -0.79
     reparations
    -0.78
     prequel
    -0.78
     Qualifier
    -0.77
     bali
    -0.76
     qualifier
    -0.76
     pleadings
    -0.76
     Tj
    -0.75
     Twp
    -0.73
    诌
    -0.73
    POSITIVE LOGITS
    itou
    0.86
     little
    0.66
     binds
    0.65
    setFlags
    0.65
     Hoff
    0.64
    ++]
    0.64
     node
    0.63
     bind
    0.62
     заку
    0.61
     more
    0.60
    Activations Density 0.096%

    No Known Activations