© 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. 797
    Prev
    Next
    INDEX
    Explanations

    featuring

    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
     this
    -2.05
     before
    -1.77
     it
    -1.53
     in
    -1.49
     there
    -1.49
     because
    -1.45
     these
    -1.43
     after
    -1.41
    したのは
    -1.40
     you
    -1.39
    POSITIVE LOGITS
     vivent
    1.55
     voient
    1.45
     Featuring
    1.42
     pourront
    1.41
    featuring
    1.39
     suivent
    1.38
     jaun
    1.38
     kurzem
    1.38
     والتي
    1.36
     savent
    1.35
    Activations Density 0.071%

    No Known Activations