© 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. 113672
    Prev
    Next
    INDEX
    Explanations

    patterns of modifiers

    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
     not
    -2.06
     mainly
    -1.60
     only
    -1.59
     use
    -1.59
     about
    -1.58
    Making
    -1.54
     first
    -1.52
    This
    -1.50
    Being
    -1.50
    Not
    -1.48
    POSITIVE LOGITS
     Dinas
    1.63
    ,
    1.59
     ☺️
    1.55
     ambigu
    1.48
    quels
    1.42
    generally
    1.38
     ABSOL
    1.36
     absolut
    1.36
     substan
    1.34
     HOR
    1.33
    Activations Density 0.449%

    No Known Activations