© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60815
    Prev
    Next
    INDEX
    Explanations

    html anchor tag starts `a href`

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

    This neuron activates on HTML anchor tags (the “a” elements, especially `<a href=…>`).

    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
    </h3>
    -1.83
     are
    -1.73
    <bos>
    -1.69
     cheminée
    -1.64
     flagrant
    -1.48
     próximo
    -1.46
    了几
    -1.46
     lintas
    -1.46
     interactiva
    -1.44
     localizado
    -1.41
    POSITIVE LOGITS
    regelen
    1.96
     unſ
    1.86
    bilden
    1.66
    諼
    1.55
    zame
    1.49
    usually
    1.48
    würdig
    1.48
    ৯
    1.45
    antası
    1.45
     story
    1.45
    Activations Density 0.005%

    No Known Activations