© 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. 10-GEMMASCOPE-RES-131K
    7. 119991
    Prev
    Next
    INDEX
    Explanations

    relative clauses and prepositional phrases

    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_10/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
     by
    -1.35
     only
    -1.19
     you
    -1.15
     eerste
    -1.08
    Становништво
    -1.01
     your
    -1.00
    𝒅
    -1.00
    >|</
    -0.98
    même
    -0.98
     peintre
    -0.98
    POSITIVE LOGITS
     Então
    1.43
    Since
    1.30
    Then
    1.27
     indietro
    1.27
    を選択します
    1.21
    While
    1.20
    newName
    1.19
     ngunit
    1.18
    During
    1.18
     Then
    1.16
    Activations Density 0.175%

    No Known Activations