© 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. 57988
    Prev
    Next
    INDEX
    Explanations

    long-term outcomes and objectives

    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
    Kelebihan
    -1.54
    Bukan
    -1.49
    kę
    -1.49
    Karakteristik
    -1.46
    Kenapa
    -1.44
    Зно
    -1.43
    Semoga
    -1.38
    ımda
    -1.37
     This
    -1.34
    OUTUBE
    -1.34
    POSITIVE LOGITS
    f
    1.47
    our
    1.45
    an
    1.44
    _
    1.38
    your
    1.30
     '
    1.30
     of
    1.30
    you
    1.30
    as
    1.27
    '
    1.27
    Activations Density 0.108%

    No Known Activations