© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130812
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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
     electricidad
    -1.27
     gingen
    -1.25
    positivos
    -1.14
     brachten
    -1.10
     cinturón
    -1.09
    寰
    -1.06
    rolley
    -1.04
    polation
    -1.03
    đu
    -1.02
    itern
    -1.02
    POSITIVE LOGITS
     new
    1.30
     could
    1.09
     other
    1.06
    最初は
    1.02
     if
    1.00
    return
    1.00
     would
    0.99
     =
    0.92
     coming
    0.91
     certainly
    0.90
    Activations Density 0.009%

    No Known Activations