© 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. 98446
    Prev
    Next
    INDEX
    Explanations

    multifunctional and versatile

    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
    ormais
    -1.21
     dziecka
    -1.12
     тільки
    -1.02
    那我
    -0.96
     aanzien
    -0.94
     sypial
    -0.94
    fellow
    -0.93
     scattata
    -0.93
     Sejarah
    -0.93
    個別
    -0.92
    POSITIVE LOGITS
     versatility
    1.23
     capabilities
    1.21
     multipurpose
    1.12
    ICIONES
    1.10
    
    1.09
    isição
    1.08
    兼
    1.08
     -
    1.08
    щина
    1.06
     multifunctional
    1.06
    Activations Density 0.065%

    No Known Activations