© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104059
    Prev
    Next
    INDEX
    Explanations

    code punctuation and identifiers

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

    line breaks or whitespace between lines of code, particularly after closing braces, brackets, or semicolons.

    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
    一些
    -1.55
     SOMETHING
    -1.38
    Some
    -1.36
    Ça
    -1.20
    SOME
    -1.19
    нау
    -1.17
     TVs
    -1.16
     we
    -1.16
    名称
    -1.14
    Nous
    -1.14
    POSITIVE LOGITS
     both
    1.39
    もあった
    1.35
     PUSTAKA
    1.31
    什么样的
    1.24
     each
    1.23
     anyone
    1.20
    而不是
    1.17
    ovým
    1.17
     каждой
    1.17
     actually
    1.16
    Activations Density 0.021%

    No Known Activations