© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73681
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -2.55
     from
    -2.50
     not
    -2.41
     of
    -2.31
     in
    -2.30
     them
    -2.23
     and
    -2.22
     which
    -2.17
     because
    -2.16
     with
    -2.09
    POSITIVE LOGITS
    8
    3.02
    6
    2.77
     {
    2.66
    \
    2.58
    黢
    2.47
    秶
    2.47
    鵙
    2.47
    읭
    2.44
    ℣
    2.41
    蹿
    2.36
    Activations Density 0.009%

    No Known Activations