© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32902
    Prev
    Next
    INDEX
    Explanations

    `pre` tag or `white-space:pre`

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

    The neuron activates on preformatted code blocks (e.g. `<pre>` tags and associated syntax-highlighting attributes).

    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
     extraña
    -1.28
    gpa
    -1.23
    collating
    -1.20
    ij
    -1.20
    mister
    -1.20
     Ekonomi
    -1.19
    ballon
    -1.18
    lapis
    -1.18
     honden
    -1.17
    薅
    -1.17
    POSITIVE LOGITS
     как
    1.63
     not
    1.34
    9
    1.26
    。　　
    1.26
    y
    1.25
    幺
    1.24
    8
    1.22
     now
    1.22
     entire
    1.21
    ).
    1.20
    Activations Density 0.016%

    No Known Activations