© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78265
    Prev
    Next
    INDEX
    Explanations

    XML doctype declarations and versions

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

    The neuron is specifically detecting the HTML/XHTML DOCTYPE public‐identifier string (e.g. the “-//W3C//DTD XHTML 1.0 Transitional//EN” declaration).

    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
     formatting
    -0.79
     lind
    -0.74
     τὰ
    -0.70
     narrativa
    -0.68
    öd
    -0.67
     boutons
    -0.67
     thema
    -0.66
     Gere
    -0.66
    Occurs
    -0.65
     Ismail
    -0.65
    POSITIVE LOGITS
     горы
    0.75
    적인
    0.71
    الع
    0.69
     quei
    0.69
    Vid
    0.68
    Global
    0.67
    Ту
    0.66
    International
    0.65
     detonation
    0.65
    zard
    0.65
    Activations Density 0.068%

    No Known Activations