© 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. 20371
    Prev
    Next
    INDEX
    Explanations

    code comments and links

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

    This neuron detects HTML tags—especially anchor (“<a …>…</a>”) markup—embedded in code comments or documentation.

    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
     expuesto
    -1.24
     depois
    -1.16
    It
    -1.15
     luego
    -1.14
     responsibility
    -1.13
    apeno
    -1.13
     dejó
    -1.12
    䊉
    -1.12
     llevo
    -1.12
     fuera
    -1.11
    POSITIVE LOGITS
     which
    1.66
     avulla
    1.29
    which
    1.24
     magasiner
    1.22
     porcelaine
    1.18
    rank
    1.16
    könig
    1.16
     जिसमें
    1.12
    )};
    1.11
     vegeta
    1.11
    Activations Density 0.300%

    No Known Activations