© 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. 10-GEMMASCOPE-RES-131K
    7. 83923
    Prev
    Next
    INDEX
    Explanations

    XSL stylesheet syntax

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

    The neuron responds wherever it sees XML‐style markup or other specialized technical tokens (e.g. XSL tag names, namespace declarations, and similarly structured code or domain-specific terms).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    </b>
    -3.63
    8
    -2.88
    4
    -2.84
    5
    -2.72
    6
    -2.58
    7
    -2.58
    x
    -2.55
    (
    -2.45
     —
    -2.39
    ”.
    -2.39
    POSITIVE LOGITS
    🫃
    3.36
    蠖
    3.25
    </h3>
    2.98
    褙
    2.56
    桫
    2.52
    铊
    2.47
    ༔
    2.45
    ︲
    2.45
    找个
    2.39
    驀
    2.39
    Activations Density 0.025%

    No Known Activations