© 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. 22-GEMMASCOPE-RES-131K
    7. 457
    Prev
    Next
    INDEX
    Explanations

    founded by

    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_22/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
     will
    -1.35
     more
    -1.27
     use
    -1.25
     suggested
    -1.23
     something
    -1.22
     prossimo
    -1.22
     additional
    -1.20
     used
    -1.19
     for
    -1.16
     while
    -1.16
    POSITIVE LOGITS
     founders
    1.19
     précédentes
    1.18
     antiguos
    1.18
     propietarios
    1.16
     poignée
    1.16
     créer
    1.16
     nacidos
    1.12
     nô
    1.11
     entrepreneurial
    1.10
     heridos
    1.09
    Activations Density 0.068%

    No Known Activations