© 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. 117763
    Prev
    Next
    INDEX
    Explanations

    multiverse and universe

    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
    該当
    -0.85
     witcher
    -0.83
     hobbit
    -0.83
    Modul
    -0.79
    天下
    -0.76
     Aralık
    -0.75
    会計
    -0.75
    TRIBUTION
    -0.74
    Год
    -0.74
    #
    -0.74
    POSITIVE LOGITS
     multiverse
    1.70
     creation
    1.54
     universe
    1.52
    multi
    1.41
     Creation
    1.36
     creator
    1.32
     existence
    1.32
     multi
    1.29
    Creation
    1.29
     Multi
    1.28
    Activations Density 0.028%

    No Known Activations