© 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. 15683
    Prev
    Next
    INDEX
    Explanations

    advanced glycation end products

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

    horizontal lines or separators in documents formed by equals signs or similar characters.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
     escond
    -2.77
    ଢ
    -2.75
    ଝ
    -2.66
    ра
    -2.42
     enamorado
    -2.42
     saltar
    -2.39
     cortar
    -2.38
     legions
    -2.27
     absurdo
    -2.27
     mentiras
    -2.25
    POSITIVE LOGITS
    ation
    2.84
    '
    2.55
    en
    2.55
    i
    2.48
    m
    2.45
    vantaged
    2.38
    e
    2.38
    臜
    2.34
    of
    2.34
    猻
    2.33
    Activations Density 0.016%

    No Known Activations