© 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. 13476
    Prev
    Next
    INDEX
    Explanations

    politicians and places

    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
     your
    -1.03
     kini
    -0.96
     here
    -0.96
     acusado
    -0.96
     at
    -0.94
     mulia
    -0.91
    bangunan
    -0.91
     escritas
    -0.90
     decoradas
    -0.89
     zatem
    -0.88
    POSITIVE LOGITS
     includ
    1.29
     område
    1.19
    JHEP
    1.14
     incluindo
    1.13
     indietro
    1.10
     estimat
    1.09
    oherty
    1.09
     attemp
    1.06
    ccoli
    1.05
    包括
    1.04
    Activations Density 0.008%

    No Known Activations