© 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. 98500
    Prev
    Next
    INDEX
    Explanations

    increased upregulated increased

    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
     правительства
    -1.29
     chré
    -1.28
     用于
    -1.18
     imágen
    -1.13
    embro
    -1.13
    UNDP
    -1.13
    estos
    -1.10
     espesor
    -1.10
     пользователей
    -1.09
     gebru
    -1.08
    POSITIVE LOGITS
     سینم
    1.19
     in
    1.19
     increase
    1.16
     both
    1.09
     ц
    1.07
     increased
    1.05
     online
    1.01
     dolore
    1.01
    Both
    1.00
    1.00
    Activations Density 0.406%
    No Known Activations