© 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. 75368
    Prev
    Next
    INDEX
    Explanations

    names and or comma

    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
     will
    -1.69
     is
    -1.52
     individuellen
    -1.46
     ursprünglichen
    -1.45
     persönlichen
    -1.40
     use
    -1.40
     direkten
    -1.38
     richtigen
    -1.30
     beiden
    -1.27
     besseren
    -1.27
    POSITIVE LOGITS
     και
    1.55
    /*---
    1.48
     gustado
    1.45
    ⑊
    1.41
     této
    1.38
    かなかった
    1.36
     klikken
    1.33
    沨
    1.31
     cérami
    1.30
    tersebut
    1.30
    Activations Density 0.014%

    No Known Activations