© 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. 93786
    Prev
    Next
    INDEX
    Explanations

    contains, includes, comprises

    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
     används
    -0.91
    زمة
    -0.86
    šana
    -0.85
     overcast
    -0.84
    Kirby
    -0.84
    addTo
    -0.84
    مرة
    -0.77
    alignSelf
    -0.75
     هستیم
    -0.75
    ❥
    -0.75
    POSITIVE LOGITS
     contains
    7.41
     contain
    6.94
    contains
    6.00
     containing
    5.97
     Contains
    5.94
    Contains
    5.81
    contain
    5.16
     содержит
    4.97
     contiene
    4.91
    包含
    4.91
    Activations Density 0.767%

    No Known Activations