© 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. 39182
    Prev
    Next
    INDEX
    Explanations

    measurement values

    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
     because
    -1.77
     these
    -1.62
     how
    -1.44
     нам
    -1.43
     our
    -1.42
     have
    -1.41
     we
    -1.38
     people
    -1.35
     will
    -1.33
    iric
    -1.33
    POSITIVE LOGITS
     that
    2.53
     significantly
    1.73
     jedynie
    1.63
     extremely
    1.60
     somewhat
    1.57
     okolo
    1.55
     amazingly
    1.53
     remarkably
    1.52
    除此
    1.52
     largely
    1.49
    Activations Density 0.200%

    No Known Activations