© 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. 42752
    Prev
    Next
    INDEX
    Explanations

    version numbers and release identifiers

    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
     reunió
    -1.50
     
    -1.42
     Tatsache
    -1.34
    marino
    -1.31
     yet
    -1.30
     its
    -1.29
     More
    -1.24
     because
    -1.24
     but
    -1.23
    kenal
    -1.20
    POSITIVE LOGITS
     brille
    1.66
     boute
    1.64
     brune
    1.61
     fraiche
    1.59
     murale
    1.58
     tatou
    1.55
     dezelve
    1.55
     assise
    1.55
    拚
    1.53
     ongles
    1.52
    Activations Density 0.075%

    No Known Activations