© 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. 107829
    Prev
    Next
    INDEX
    Explanations

    entitled or titled methods

    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
     when
    -1.19
     摄影
    -0.98
     other
    -0.97
     Vikipedi
    -0.94
     sabia
    -0.92
     dibutuhkan
    -0.90
    時には
    -0.90
    쩔
    -0.89
     reflexão
    -0.88
     because
    -0.88
    POSITIVE LOGITS
    方法
    1.99
     method
    1.91
     methods
    1.90
    Methods
    1.56
    methods
    1.55
     Methods
    1.48
     Method
    1.48
     방법
    1.47
    method
    1.45
    METHOD
    1.45
    Activations Density 0.157%

    No Known Activations