© 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. 72271
    Prev
    Next
    INDEX
    Explanations

    compound words and phrases

    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
    danke
    -1.09
    gruss
    -1.09
    ACIONES
    -1.07
     içeris
    -1.01
    Также
    -1.01
    Tại
    -1.00
     каже
    -1.00
    gleichen
    -1.00
    sprzedam
    -1.00
     мою
    -1.00
    POSITIVE LOGITS
     all
    1.34
    
    1.10
     by
    1.09
    一遍
    1.06
    leyball
    1.05
    邉
    1.05
    ૫
    1.05
     např
    1.04
     tæt
    1.01
    中島
    1.00
    Activations Density 0.044%

    No Known Activations