© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102517
    Prev
    Next
    INDEX
    Explanations

    code tags and programming constructs

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

    HTML/XML tags and mathematical/chemical notation with angle brackets or square brackets.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on HTML emphasis tags, especially the opening `<strong>` tag.

    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
     It
    -1.97
     In
    -1.95
     have
    -1.80
     trochę
    -1.77
     by
    -1.75
     recoge
    -1.74
     my
    -1.74
     an
    -1.73
     a
    -1.73
     more
    -1.71
    POSITIVE LOGITS
     kvalitet
    2.28
     meren
    2.22
     kalem
    2.16
     diki
    2.14
     aktiviteter
    2.11
     akti
    2.08
     namn
    2.03
     språk
    2.02
     bidra
    2.00
     medier
    1.99
    Activations Density 0.006%

    No Known Activations