© 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. 22-GEMMASCOPE-RES-131K
    7. 67974
    Prev
    Next
    INDEX
    Explanations

    welcome, climates, celebrates, adequate, speed

    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
     principalmente
    -1.37
     głównie
    -1.32
    있는
    -1.05
     principalement
    -1.03
     많은
    -0.98
    もあって
    -0.98
     灰色
    -0.97
     gimana
    -0.96
     konnten
    -0.96
     nebst
    -0.95
    POSITIVE LOGITS
     ideia
    1.20
    荣耀
    1.18
    暧
    1.16
    Ⓒ
    1.16
    shaders
    1.16
     الکترون
    1.16
    
    1.13
     osv
    1.12
     hitherto
    1.12
     imagem
    1.11
    Activations Density 0.318%

    No Known Activations