© 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. 104085
    Prev
    Next
    INDEX
    Explanations

    years

    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
     you
    -1.70
     Infór
    -1.57
    Aiheesta
    -1.48
    tichetta
    -1.40
    enfone
    -1.39
    訁
    -1.38
     but
    -1.34
     nyní
    -1.34
     sarà
    -1.33
    ieR
    -1.33
    POSITIVE LOGITS
    ↵
    1.52
    1.30
     ultra
    1.26
    :
    1.25
    らなかった
    1.23
     From
    1.22
     ikke
    1.21
     We
    1.21
    
    1.19
    just
    1.16
    Activations Density 0.132%
    No Known Activations