© 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. 127
    Prev
    Next
    INDEX
    Explanations

    possessive and specific phrases

    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
    七年
    -1.67
     donker
    -1.59
     of
    -1.47
     schermata
    -1.46
    攸
    -1.42
     then
    -1.40
     émission
    -1.40
    恕
    -1.37
     grijs
    -1.34
    énus
    -1.34
    POSITIVE LOGITS
    готовление
    1.55
     brinda
    1.46
     obstante
    1.45
     to
    1.43
     esfuer
    1.38
     wirklich
    1.38
     großer
    1.38
    跸
    1.34
    nextProps
    1.33
    変な
    1.27
    Activations Density 0.007%

    No Known Activations