© 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. 119603
    Prev
    Next
    INDEX
    Explanations

    specific location names

    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
     něko
    -1.43
     ſon
    -1.42
    viated
    -1.34
    𖧵
    -1.30
     např
    -1.29
    taires
    -1.26
    Hanya
    -1.26
     kapak
    -1.26
    個人的に
    -1.24
     apont
    -1.24
    POSITIVE LOGITS
     we
    1.48
    .
    1.38
     data
    1.27
    ERIE
    1.18
     Wohnungen
    1.18
     they
    1.16
     not
    1.16
     use
    1.13
     projects
    1.13
     then
    1.12
    Activations Density 0.030%

    No Known Activations