© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 38930
    Prev
    Next
    INDEX
    Explanations

    code identifiers and declarations

    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
     keram
    -2.08
     silikon
    -1.98
     balkon
    -1.98
     kompleks
    -1.92
     kompres
    -1.88
    蟊
    -1.88
     gummy
    -1.87
     krem
    -1.84
     dát
    -1.84
     triko
    -1.82
    POSITIVE LOGITS
     has
    2.19
     with
    2.02
     and
    1.87
     for
    1.86
     is
    1.84
     For
    1.74
     helps
    1.63
     helped
    1.63
     as
    1.59
     made
    1.59
    Activations Density 0.017%

    No Known Activations