© 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. 34-GEMMASCOPE-RES-131K
    7. 118319
    Prev
    Next
    INDEX
    Explanations

    references to Johnson

    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_34/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
     huo
    -0.91
     happily
    -0.91
     Katsu
    -0.90
     núcleos
    -0.89
     giu
    -0.87
     Flur
    -0.87
     ote
    -0.87
     Tó
    -0.86
     ſhall
    -0.85
     tejido
    -0.85
    POSITIVE LOGITS
    baugh
    1.38
    burg
    1.01
     pave
    0.94
    )?;
    0.90
    BURG
    0.90
     ezzel
    0.90
    uchter
    0.90
     tweaking
    0.88
     الكه
    0.87
     martes
    0.87
    Activations Density 0.007%

    No Known Activations