© 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. 34-GEMMASCOPE-RES-131K
    7. 31608
    Prev
    Next
    INDEX
    Explanations

    product qualities and functionality

    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_34/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
    した場合
    -0.88
     бесплатно
    -0.83
     економі
    -0.82
     витра
    -0.81
    帶來
    -0.79
    的情況
    -0.79
     nếu
    -0.78
    AJAS
    -0.78
     廠
    -0.78
     يعمل
    -0.77
    POSITIVE LOGITS
     quality
    1.56
     functional
    1.37
    QUALITY
    1.27
     FUNCTION
    1.25
     everyday
    1.19
     functionality
    1.16
     QUALITY
    1.15
     attainable
    1.13
     Quality
    1.12
    fonction
    1.08
    Activations Density 0.052%

    No Known Activations