© 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. 70643
    Prev
    Next
    INDEX
    Explanations

    journalist, author, etc

    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
     artikkelen
    -1.27
    なのかな
    -1.12
    なのでしょう
    -1.07
     gustar
    -1.03
     saisi
    -1.03
     costura
    -1.00
     bordado
    -1.00
     bordada
    -0.99
    foreignKey
    -0.99
    OOTDTY
    -0.98
    POSITIVE LOGITS
     &
    1.08
    が
    1.02
     etc
    0.99
     amd
    0.99
     evtl
    0.97
    atize
    0.95
    ''
    0.91
    lihood
    0.90
     ağaç
    0.89
     überall
    0.88
    Activations Density 0.005%

    No Known Activations