© 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. 130281
    Prev
    Next
    INDEX
    Explanations

    growth and decline

    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
     so
    -1.96
     or
    -1.79
     seems
    -1.75
     what
    -1.64
     could
    -1.63
     out
    -1.49
     should
    -1.49
     seemed
    -1.48
     before
    -1.46
     having
    -1.41
    POSITIVE LOGITS
     méda
    1.56
     łyż
    1.45
     menjelaskan
    1.41
     merveilleux
    1.41
     ALSO
    1.40
     poêle
    1.38
     rafraî
    1.32
     alho
    1.31
     vatten
    1.31
     cinq
    1.31
    Activations Density 0.115%

    No Known Activations