© 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. 69456
    Prev
    Next
    INDEX
    Explanations

    extent, best, fullest, possible

    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
    )
    -1.64
     voyageurs
    -1.42
     habitants
    -1.41
    镦
    -1.40
     Strukt
    -1.37
    蔀
    -1.36
     Saltar
    -1.34
    厲害
    -1.32
     père
    -1.29
    unggah
    -1.29
    POSITIVE LOGITS
     or
    1.74
    ↵
    1.69
     حتی
    1.58
     atau
    1.50
    st
    1.48
     Ã
    1.48
     يش
    1.44
    を越
    1.42
    6
    1.41
    ündigung
    1.41
    Activations Density 0.003%

    No Known Activations