© 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. 114106
    Prev
    Next
    INDEX
    Explanations

    html break tags

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

    HTML line break tags (`<br>` or `<br/>`).

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
    ":
    -1.46
    nellement
    -1.41
    ’,
    -1.41
     '/':
    -1.40
    влено
    -1.40
    einer
    -1.38
     pleas
    -1.36
    ֹת
    -1.35
    :"-"`
    -1.34
     ditangkap
    -1.33
    POSITIVE LOGITS
     neón
    1.77
     "
    1.65
     '
    1.40
     alojamientos
    1.40
     dritte
    1.37
     sostener
    1.34
     hermosos
    1.33
     rigue
    1.33
     acoged
    1.33
     sacerdote
    1.32
    Activations Density 0.029%

    No Known Activations