© 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. 22-GEMMASCOPE-RES-131K
    7. 104441
    Prev
    Next
    INDEX
    Explanations

    court orders, injunctions, and stays

    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_22/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
    apatalk
    -1.10
     наконец
    -1.05
    ₆
    -1.01
     através
    -0.99
    absorb
    -0.98
     interacción
    -0.97
    amigo
    -0.95
    saus
    -0.94
     klarer
    -0.94
     borbo
    -0.93
    POSITIVE LOGITS
    ּוֹ
    1.35
    něte
    1.30
     requested
    1.26
    ֑
    1.26
    ַּ
    1.20
     voordat
    1.18
    ִּ
    1.16
     menjalankan
    1.14
     before
    1.13
     slechts
    1.12
    Activations Density 0.041%

    No Known Activations