© 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. 110981
    Prev
    Next
    INDEX
    Explanations

    Java libraries

    np_acts-logits-general · gemini-2.5-flash-lite

    code related to object-relational mapping (ORM) frameworks and database session management.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     skole
    -1.48
     eksklu
    -1.45
     elektri
    -1.44
     rollen
    -1.43
     ideen
    -1.41
     gewo
    -1.41
     respek
    -1.40
     umo
    -1.40
     navn
    -1.39
     infrastruktur
    -1.38
    POSITIVE LOGITS
    )
    1.55
    Of
    1.48
     как
    1.38
    Don
    1.34
     probado
    1.29
     أو
    1.23
     don
    1.20
    /
    1.20
    Fact
    1.18
    What
    1.17
    Activations Density 0.021%

    No Known Activations