© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83371
    Prev
    Next
    INDEX
    Explanations

    learning activities

    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
    暱
    -0.93
     Postgraduate
    -0.86
    不錯
    -0.82
    紀錄
    -0.82
     postgraduate
    -0.81
    soby
    -0.79
    兩種
    -0.79
     университе
    -0.79
     pomeriggio
    -0.79
     大学
    -0.79
    POSITIVE LOGITS
     units
    1.37
     unit
    1.31
     integrated
    1.28
     integrate
    1.27
     lessons
    1.23
     integrating
    1.22
     inquiry
    1.22
     integrates
    1.21
    Units
    1.21
     Units
    1.20
    Activations Density 0.040%

    No Known Activations