© 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. 12040
    Prev
    Next
    INDEX
    Explanations

    HTML tags

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

    HTML/XML markup tags and code formatting elements like angle brackets, tags, and indentation.

    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
     to
    -2.33
     tačiau
    -1.45
     соответству
    -1.34
     it
    -1.30
     люди
    -1.27
    >
    -1.22
     during
    -1.17
     is
    -1.17
    也是
    -1.17
    },
    -1.16
    POSITIVE LOGITS
    IMPORTANT
    1.49
     otwor
    1.32
    tellingen
    1.31
     REMOVE
    1.30
     رغم
    1.23
    ができます
    1.23
    additional
    1.22
     másik
    1.22
    OTHER
    1.20
     написать
    1.20
    Activations Density 0.031%

    No Known Activations