© 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. 101974
    Prev
    Next
    INDEX
    Explanations

    Workers fight closure

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

    The neuron activates on markup delimiters (e.g. HTML tags like <em> or <strong> and LaTeX math markers like `$`).

    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
    ."
    -2.23
     And
    -1.84
     and
    -1.80
     "
    -1.77
     '
    -1.72
     After
    -1.65
     also
    -1.59
     but
    -1.59
     At
    -1.59
     Both
    -1.53
    POSITIVE LOGITS
    秶
    2.19
    
    1.78
    牐
    1.71
    犼
    1.67
    ionali
    1.67
     vixion
    1.66
    before
    1.65
    땜
    1.63
    睃
    1.62
    6
    1.60
    Activations Density 0.000%

    No Known Activations