© 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. 80760
    Prev
    Next
    INDEX
    Explanations

    shed any, waived any

    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
     nogle
    -1.19
     bazı
    -1.16
     einzelnen
    -1.10
    บ้าง
    -1.06
     algunas
    -1.05
    Ȥ
    -1.04
    わせて
    -1.02
    的一些
    -0.98
    livet
    -0.96
     algunos
    -0.96
    POSITIVE LOGITS
     any
    5.75
    任何
    3.78
     cualquier
    3.77
    Any
    3.47
     qualquer
    3.34
     wszel
    3.14
    any
    3.00
     qualsiasi
    2.86
     Any
    2.80
     orice
    2.67
    Activations Density 0.082%

    No Known Activations