© 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. 119538
    Prev
    Next
    INDEX
    Explanations

    note-taking software and organization

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

    references to note-taking, writing, or document management applications and tools.

    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
     but
    -1.52
     pero
    -1.25
    ↵
    -1.23
     gül
    -1.21
     pam
    -1.21
     conditions
    -1.20
    solt
    -1.18
     she
    -1.17
     masculina
    -1.17
     komplett
    -1.16
    POSITIVE LOGITS
     داشته
    1.27
     iveco
    1.25
    ция
    1.24
     dreapta
    1.19
     asemenea
    1.16
     ducato
    1.14
     felipe
    1.14
     daihatsu
    1.13
     moschino
    1.13
    줍
    1.13
    Activations Density 0.094%

    No Known Activations