© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100267
    Prev
    Next
    INDEX
    Explanations

    code expressions and attributes

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

    punctuation marks in programming code, especially closing brackets, parentheses, and quotes.

    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
     here
    -1.27
     vinci
    -1.27
    Ⓡ
    -1.26
    好用
    -1.24
     etui
    -1.20
    MYSQL
    -1.18
     darm
    -1.15
     auffi
    -1.13
     falda
    -1.13
     hond
    -1.12
    POSITIVE LOGITS
     to
    1.44
     jeweiligen
    1.36
    Considering
    1.23
     sicheren
    1.23
     raczej
    1.22
     entsprechenden
    1.21
     Öffentlich
    1.16
    ),
    1.16
     It
    1.15
    すでに
    1.14
    Activations Density 0.094%

    No Known Activations