© 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. 110881
    Prev
    Next
    INDEX
    Explanations

    locale, version, features

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

    technical tokens in code and data files, particularly those related to CLDR (Common Locale Data Repository) and locale/internationalization systems.

    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
    ilization
    -1.58
    甞
    -1.48
    teryx
    -1.41
    ᥫ
    -1.41
    ꜆
    -1.41
    ครื่อง
    -1.40
    貘
    -1.37
     clínicos
    -1.36
    ceptibility
    -1.34
     noastre
    -1.34
    POSITIVE LOGITS
    3
    1.63
     esimerkiksi
    1.62
     for
    1.47
    0
    1.46
    AL
    1.42
    7
    1.39
     небольшой
    1.38
    6
    1.33
     qualche
    1.32
     如
    1.31
    Activations Density 0.005%

    No Known Activations