© 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. 104110
    Prev
    Next
    INDEX
    Explanations

    web archives

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

    references to "Archive" in the context of digital archives and URLs (like Internet Archive, archive.org, archive.is).

    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
    ↵↵
    -1.71
     utilizados
    -1.58
    ⩕
    -1.39
    inerary
    -1.38
     utilizado
    -1.36
     specialized
    -1.35
    出来る
    -1.34
     etwa
    -1.32
     スカイ
    -1.31
     gând
    -1.30
    POSITIVE LOGITS
     \
    1.49
    夀
    1.38
    ஂ
    1.37
     ''
    1.30
     '
    1.30
    =!
    1.29
     «
    1.27
     presidencia
    1.23
    gemeinden
    1.23
     vertes
    1.23
    Activations Density 0.019%

    No Known Activations