© 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. 102322
    Prev
    Next
    INDEX
    Explanations

    java package names or domain names

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

    the token "com" in code, configuration files, and technical documentation (especially in reverse domain notation like "com.example.app").

    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
    事も
    -2.75
    谞
    -2.56
    INTAIN
    -2.41
    見つ
    -2.27
    Maar
    -2.27
    most
    -2.27
    事は
    -2.25
    PLICATE
    -2.25
    ременно
    -2.25
     specify
    -2.25
    POSITIVE LOGITS
    zelfde
    2.56
    的在
    2.48
    絅
    2.45
     {
    2.42
    n
    2.41
     "
    2.39
    鰱
    2.38
    0
    2.30
    en
    2.25
    y
    2.22
    Activations Density 0.069%

    No Known Activations