© 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. 78960
    Prev
    Next
    INDEX
    Explanations

    HTML head tag

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

    The neuron is responsive to HTML/XML tag syntax, peaking on the angle‐bracket delimiters of tags (e.g. “<html>”).

    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
     kwe
    -0.91
    macher
    -0.85
     oeuvres
    -0.84
    IED
    -0.83
     solteiro
    -0.82
     ESPECIAL
    -0.82
     恵
    -0.81
     puissiez
    -0.80
    хотво
    -0.79
     pacient
    -0.79
    POSITIVE LOGITS
     head
    1.53
    head
    1.38
     heads
    1.13
     Head
    1.09
    ヘッド
    1.05
    Head
    1.03
     HEAD
    0.91
    asers
    0.90
     Kopf
    0.85
     cabeza
    0.82
    Activations Density 0.058%

    No Known Activations