© 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. 93604
    Prev
    Next
    INDEX
    Explanations

    life and living standards

    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
    称呼
    -0.84
    maxLength
    -0.82
    áln
    -0.81
     texinfo
    -0.80
    成功的
    -0.80
     vectorielles
    -0.79
    Trọng
    -0.79
    ênd
    -0.77
     vpon
    -0.76
    沏
    -0.76
    POSITIVE LOGITS
     living
    2.53
     lifestyle
    2.23
     standard
    2.16
     standards
    2.11
    生活
    1.88
    的生活
    1.80
    standard
    1.77
    standards
    1.73
    living
    1.70
     life
    1.64
    Activations Density 0.021%

    No Known Activations