© 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. 65179
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     but
    -1.61
     and
    -1.42
     natomiast
    -1.38
    ditionally
    -1.34
     wundersch
    -1.26
     was
    -1.23
     تھے
    -1.21
     had
    -1.17
     first
    -1.14
     But
    -1.14
    POSITIVE LOGITS
     означает
    1.28
     Că
    1.27
     Vía
    1.27
     malen
    1.23
    гий
    1.21
     sommet
    1.20
     interdit
    1.20
     siis
    1.19
    álise
    1.18
     galeria
    1.17
    Activations Density 0.005%

    No Known Activations