© 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. 10-GEMMASCOPE-RES-131K
    7. 113561
    Prev
    Next
    INDEX
    Explanations

    US senators and representatives

    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
    ≦
    -1.35
    Ď
    -1.26
    кисло
    -1.23
     либо
    -1.23
    协会
    -1.22
     visitó
    -1.22
     
    -1.20
    DICTION
    -1.15
     конечно
    -1.13
     THE
    -1.13
    POSITIVE LOGITS
    quần
    1.47
    bước
    1.40
    
    1.37
    〟
    1.35
    ￬
    1.35
    phòng
    1.34
     entusias
    1.34
    đồ
    1.34
    bảng
    1.34
    đại
    1.29
    Activations Density 0.039%

    No Known Activations