© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42313
    Prev
    Next
    INDEX
    Explanations

    city names and 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
    Different
    -1.84
     различни
    -1.52
    Nowadays
    -1.43
     أيضا
    -1.42
    ledning
    -1.38
     Nowadays
    -1.36
    Lalu
    -1.35
    Customized
    -1.34
     déchir
    -1.34
    🍡
    -1.32
    POSITIVE LOGITS
     its
    1.91
     “
    1.77
     be
    1.64
     "
    1.63
     will
    1.56
     your
    1.48
     però
    1.44
     anything
    1.44
    ’
    1.43
     «
    1.38
    Activations Density 0.122%

    No Known Activations