© 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. 22-GEMMASCOPE-RES-131K
    7. 73232
    Prev
    Next
    INDEX
    Explanations

    code, data types, and configuration

    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_22/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
    -1.95
     now
    -1.95
     both
    -1.83
     almost
    -1.79
     people
    -1.77
     this
    -1.75
     undeniably
    -1.74
     mostly
    -1.70
     five
    -1.67
     in
    -1.66
    POSITIVE LOGITS
     wondrous
    1.45
     Dinas
    1.42
     myriad
    1.41
     horrid
    1.38
    every
    1.34
     offiziell
    1.34
     strikingly
    1.34
     ACTUAL
    1.32
     startling
    1.31
     boister
    1.30
    Activations Density 0.010%

    No Known Activations