© 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. 39958
    Prev
    Next
    INDEX
    Explanations

    multi-linguals

    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
     activities
    -1.30
     activity
    -1.27
     they
    -1.22
     this
    -1.18
     development
    -1.14
     fusca
    -1.14
    碌
    -1.11
     rouse
    -1.07
     żeby
    -1.07
    海道
    -1.07
    POSITIVE LOGITS
    打造
    1.27
    Čes
    1.24
     nimmer
    1.21
     nadru
    1.20
     ингреди
    1.19
     három
    1.17
     a
    1.14
     négy
    1.12
     maravilhoso
    1.11
    asına
    1.09
    Activations Density 0.005%

    No Known Activations