© 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. 10-GEMMASCOPE-RES-131K
    7. 99554
    Prev
    Next
    INDEX
    Explanations

    HTML anchor links

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

    The neuron detects HTML attribute assignments (especially anchor href="#" or similar quoted attribute‐value pairs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    b
    -1.74
    ve
    -1.66
    使用的
    -1.63
     camiset
    -1.59
    q
    -1.58
     очень
    -1.58
     that
    -1.55
    0
    -1.52
     довольно
    -1.50
    太多了
    -1.50
    POSITIVE LOGITS
    гії
    1.95
    </h3>
    1.68
    gmd
    1.63
    </h1>
    1.62
    皲
    1.61
     portavoz
    1.58
     planea
    1.52
     Там
    1.52
    プレス
    1.52
    Leather
    1.45
    Activations Density 0.002%

    No Known Activations