© 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. 79641
    Prev
    Next
    INDEX
    Explanations

    Names of people

    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
    Metode
    -1.50
     colonie
    -1.45
    Präsident
    -1.41
     ponga
    -1.41
     tonel
    -1.41
     étage
    -1.41
     canciones
    -1.38
     policia
    -1.37
    Obr
    -1.34
    درب
    -1.34
    POSITIVE LOGITS
     “
    1.81
     "
    1.63
     of
    1.48
     A
    1.46
     to
    1.45
     Joseph
    1.43
     Michael
    1.39
     Andrew
    1.38
     David
    1.36
     James
    1.35
    Activations Density 0.020%

    No Known Activations