© 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. 10-GEMMASCOPE-RES-131K
    7. 9193
    Prev
    Next
    INDEX
    Explanations

    language context switching

    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_10/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
    still
    -1.34
    Cars
    -1.25
    CELONA
    -1.17
    isées
    -1.17
    currently
    -1.15
    ism
    -1.12
    >>>>>>
    -1.12
    welcome
    -1.11
    sequently
    -1.09
    鲫
    -1.09
    POSITIVE LOGITS
     about
    1.51
     with
    1.27
     dėl
    1.24
     darstellt
    1.22
     sejak
    1.20
    ͔
    1.16
    もいい
    1.16
     demostrado
    1.15
     perdido
    1.14
     veículo
    1.14
    Activations Density 0.083%

    No Known Activations