© 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. 58111
    Prev
    Next
    INDEX
    Explanations

    code examples and documentation

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

    This neuron detects markup formatting tokens (e.g., markdown emphasis like `**` or backticks and similar HTML/markup tags).

    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
     lequel
    -1.59
     investissement
    -1.55
     appareil
    -1.45
     maravilh
    -1.40
    الان
    -1.37
     femininas
    -1.37
    Dlaczego
    -1.31
    Maintenant
    -1.31
    ほうがいい
    -1.31
    zember
    -1.30
    POSITIVE LOGITS
     know
    1.66
    不算
    1.38
     what
    1.34
     NOT
    1.34
    to
    1.30
    最后由
    1.28
     wasn
    1.26
     mentre
    1.26
     NO
    1.24
     WHAT
    1.24
    Activations Density 0.012%

    No Known Activations