© 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. 22-GEMMASCOPE-RES-131K
    4. 69265
    Prev
    Next
    INDEX
    Explanations

    section, category, or page headings

    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
     damaligen
    -1.24
    alanta
    -1.23
     مشکی
    -1.17
     Hauptstadt
    -1.16
     szkoły
    -1.13
     Luglio
    -1.12
    élite
    -1.12
     Послед
    -1.10
    XCTAssert
    -1.08
     Projektu
    -1.05
    POSITIVE LOGITS
     présentation
    1.24
    AKB
    1.23
    cestry
    1.20
     biblia
    1.20
     inmig
    1.16
    tismo
    1.16
     ilegal
    1.15
    Ἱ
    1.14
    cestors
    1.14
    omalies
    1.14
    Activations Density 0.019%

    No Known Activations