© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90842
    Prev
    Next
    INDEX
    Explanations

    html attributes

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

    The neuron fires on quoted attribute values inside HTML tags (e.g. the strings in quotes after = in link/script tags).

    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
    ことはありません
    -1.11
     férfi
    -1.11
     QUÉ
    -1.09
     CONCEP
    -1.09
     maquiagem
    -1.09
     méret
    -1.07
     MÁS
    -1.06
     mélang
    -1.05
     alkot
    -1.04
    Материал
    -1.03
    POSITIVE LOGITS
     type
    1.13
     but
    0.98
     where
    0.92
     can
    0.91
     towards
    0.91
     against
    0.88
     though
    0.88
     at
    0.86
    \\
    0.85
    type
    0.82
    Activations Density 0.025%

    No Known Activations