© 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. 54304
    Prev
    Next
    INDEX
    Explanations

    programming code and specific entities

    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
     any
    -1.02
    ORETICAL
    -1.01
     every
    -1.00
    эш
    -1.00
    𝖔
    -0.96
    Поэтому
    -0.96
     обеспечить
    -0.96
     while
    -0.95
     by
    -0.94
    二郎
    -0.94
    POSITIVE LOGITS
    都需要
    1.05
     surtido
    1.01
     supuestamente
    1.00
    指的是
    0.98
    謾
    0.98
     positiva
    0.92
     alinea
    0.92
     adecuados
    0.92
    "../
    0.91
    并非
    0.91
    Activations Density 0.004%

    No Known Activations