© 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. 75569
    Prev
    Next
    INDEX
    Explanations

    renting various items and spaces

    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
    šné
    -1.65
     flotante
    -1.59
     URBAN
    -1.54
     sabem
    -1.48
     barcel
    -1.44
    鎰
    -1.43
     volet
    -1.42
     koja
    -1.39
     “¿
    -1.37
     Améli
    -1.36
    POSITIVE LOGITS
     for
    1.72
     some
    1.61
     not
    1.55
     new
    1.55
    9
    1.54
     renting
    1.51
     this
    1.42
     now
    1.38
     already
    1.37
     bereits
    1.36
    Activations Density 0.027%

    No Known Activations