© 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. 89900
    Prev
    Next
    INDEX
    Explanations

    court names and declarations

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

    This neuron responds to XML/HTML‐style tag and attribute names (e.g. translation, Name, Type, FullName) in markup.

    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
    --
    -0.96
     TAP
    -0.84
     tiles
    -0.78
     ล
    -0.78
     дня
    -0.76
     يكون
    -0.76
     ron
    -0.76
    "
    -0.75
     😍
    -0.75
    マル
    -0.74
    POSITIVE LOGITS
     mềm
    1.05
     čet
    0.95
     démocr
    0.92
     concorda
    0.91
    ンドン
    0.90
     SITY
    0.88
    ೩
    0.87
    yecek
    0.86
    klere
    0.86
     海鮮
    0.85
    Activations Density 0.001%

    No Known Activations