© 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. 72345
    Prev
    Next
    INDEX
    Explanations

    code imports 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_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
     COVID
    -1.72
     covid
    -1.56
     Covid
    -1.55
     ২০
    -1.41
    Covid
    -1.37
    covid
    -1.35
    COVID
    -1.34
     Biden
    -1.34
    プター
    -1.22
     metaverse
    -1.18
    POSITIVE LOGITS
     up
    1.34
     center
    1.11
     how
    1.09
     you
    1.09
     with
    1.07
     — 
    1.05
    glyphicon
    1.01
     equal
    1.00
     places
    0.99
     however
    0.96
    Activations Density 0.105%

    No Known Activations