© 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. 10-GEMMASCOPE-RES-131K
    7. 20277
    Prev
    Next
    INDEX
    Explanations

    New Zealand and Ireland locations

    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_10/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
     ahol
    -1.32
    IZACIÓN
    -1.23
     rác
    -1.20
     выбирать
    -1.15
     organized
    -1.12
    eradish
    -1.12
    larger
    -1.11
    ierten
    -1.11
     Kingdom
    -1.10
    ۡ
    -1.10
    POSITIVE LOGITS
    6
    1.34
    </h4>
    1.20
    z
    1.20
     друго
    1.13
     archiv
    1.11
    3
    1.10
     into
    1.08
     gefallen
    1.07
     geschafft
    1.05
     przecież
    1.05
    Activations Density 0.008%

    No Known Activations