© 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. 22702
    Prev
    Next
    INDEX
    Explanations

    math and science notation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Karakteristik
    -2.02
    Kemudian
    -1.97
    Fungsi
    -1.90
    Sekarang
    -1.80
    Sebelum
    -1.78
    Siapa
    -1.77
    Krank
    -1.77
    𖤣
    -1.75
    琹
    -1.73
    Langkah
    -1.72
    POSITIVE LOGITS
    ’
    2.42
     to
    2.36
    _
    2.31
    %;
    1.95
    '
    1.88
    >
    1.85
    \
    1.84
    :][
    1.81
    S
    1.80
    W
    1.79
    Activations Density 0.002%

    No Known Activations