© 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. 2268
    Prev
    Next
    INDEX
    Explanations

    `in` or `∈` checks

    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
     eingeführt
    -0.90
    τικά
    -0.87
    ⿰
    -0.87
     gemacht
    -0.86
     glede
    -0.82
     extinción
    -0.81
     tracción
    -0.80
    特有
    -0.79
     isInitialized
    -0.79
     exceso
    -0.79
    POSITIVE LOGITS
     in
    4.25
     ∈
    1.99
    ∈
    1.80
     belongs
    1.60
    in
    1.53
     belong
    1.52
     dalam
    1.45
     In
    1.44
     belonging
    1.41
     isIn
    1.38
    Activations Density 0.050%

    No Known Activations