© 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. 12150
    Prev
    Next
    INDEX
    Explanations

    city and bay

    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
     when
    -1.96
     where
    -1.70
     quickly
    -1.66
     with
    -1.63
     which
    -1.63
     using
    -1.62
     especially
    -1.53
     between
    -1.52
     that
    -1.48
     both
    -1.47
    POSITIVE LOGITS
     SUCH
    1.43
    trying
    1.38
    represents
    1.36
     нынеш
    1.35
     SAME
    1.34
     tente
    1.33
    recently
    1.32
     сегодняш
    1.30
    previously
    1.29
    wasn
    1.29
    Activations Density 0.160%

    No Known Activations