© 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. 118856
    Prev
    Next
    INDEX
    Explanations

    franchise or school history

    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
     It
    -1.41
    čního
    -1.41
     SizedBox
    -1.37
     now
    -1.32
     그의
    -1.29
     втором
    -1.29
    sữa
    -1.27
    ümüz
    -1.27
     náš
    -1.27
    ってました
    -1.24
    POSITIVE LOGITS
    ’
    1.34
     lemah
    1.27
     turun
    1.24
     veren
    1.23
    лона
    1.23
     vandal
    1.23
     aktivi
    1.20
    اين
    1.20
    Initially
    1.18
     burbu
    1.18
    Activations Density 0.054%

    No Known Activations