© 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. 120106
    Prev
    Next
    INDEX
    Explanations

    code headers and technical descriptions

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

    the word "#region" in code files, which marks the beginning of a collapsible code section.

    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
    銪
    -1.79
    ᕱ
    -1.60
     “
    -1.59
     They
    -1.56
    訁
    -1.54
    ちなみに
    -1.51
    ⚢
    -1.51
    {
    -1.49
     “[
    -1.45
    ”
    -1.45
    POSITIVE LOGITS
     of
    2.20
     to
    1.85
    忖
    1.54
     PUSTAKA
    1.51
     that
    1.44
    ZIONE
    1.38
    єр
    1.37
    führen
    1.33
    metries
    1.32
    ᶤ
    1.31
    Activations Density 0.000%

    No Known Activations