© 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. 90696
    Prev
    Next
    INDEX
    Explanations

    names, dates, and deaths

    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
     Manten
    -1.24
     botão
    -1.23
     abenço
    -1.22
     dacia
    -1.21
     Ikan
    -1.20
    —(
    -1.18
     exercício
    -1.17
     抠
    -1.17
     gän
    -1.17
     Estudiantes
    -1.16
    POSITIVE LOGITS
    gangss
    1.33
     fortsätter
    1.23
     bonitas
    1.14
     htons
    1.13
     William
    1.13
     George
    1.12
     Y
    1.07
     behövs
    1.06
     информацию
    1.05
     ricas
    1.05
    Activations Density 0.016%

    No Known Activations