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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11522
    Prev
    Next
    INDEX
    Explanations

    "I" or "you" questions, abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ִּ
    -1.23
     سنوات
    -1.16
     particolarmente
    -1.14
      
    -1.13
    konos
    -1.12
     especially
    -1.10
     soprattutto
    -1.08
     イエロー
    -1.06
     особен
    -1.05
    assertArray
    -1.04
    POSITIVE LOGITS
     everything
    1.48
     only
    1.29
     nothing
    1.28
    Ошибка
    1.27
    ◆◆
    1.27
    ()")
    1.21
    ()",
    1.20
     all
    1.20
     rús
    1.18
    ಛ
    1.17
    Activations Density 0.027%

    No Known Activations