© 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. 22-GEMMASCOPE-RES-131K
    7. 65489
    Prev
    Next
    INDEX
    Explanations

    HTML link href

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

    The neuron fires on HTML/XML markup tags—especially on opening‐tag attribute boundaries like the `">` ending link (`<a href=…">`) or string (`<string name=…">`) definitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     this
    -1.44
     whoever
    -1.27
     between
    -1.15
     those
    -1.06
     when
    -1.06
     whose
    -1.06
     what
    -1.05
     these
    -1.03
     that
    -1.01
     identical
    -0.99
    POSITIVE LOGITS
     seleccione
    1.14
    靂
    1.09
     pagină
    1.09
     haremos
    1.03
     Thule
    1.02
    Substance
    1.00
     gti
    1.00
    Retrieve
    0.98
    쿡
    0.98
     butyl
    0.97
    Activations Density 0.002%

    No Known Activations