© 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. 99987
    Prev
    Next
    INDEX
    Explanations

    common abbreviations and initialisms

    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
     to
    -3.05
     by
    -2.80
     with
    -2.66
     before
    -2.59
     on
    -2.55
     in
    -2.47
     when
    -2.45
     through
    -2.42
     or
    -2.23
     should
    -2.23
    POSITIVE LOGITS
     bross
    1.98
     bricola
    1.98
    鹟
    1.96
     participer
    1.89
     appels
    1.87
     türkiye
    1.84
     pè
    1.83
     diriger
    1.80
     Dinas
    1.80
     palme
    1.80
    Activations Density 0.075%

    No Known Activations