© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15643
    Prev
    Next
    INDEX
    Explanations

    URL parameters

    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
     Président
    -1.47
    
    -1.43
    aroma
    -1.41
    меди
    -1.41
     kommende
    -1.39
    などが
    -1.38
    сама
    -1.38
    kalender
    -1.34
     vont
    -1.33
     berge
    -1.33
    POSITIVE LOGITS
    C
    1.57
    tedì
    1.43
    最初から
    1.38
    L
    1.38
     name
    1.34
    M
    1.34
     then
    1.34
    で見る
    1.29
    From
    1.26
     \&
    1.24
    Activations Density 0.007%

    No Known Activations