© 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. 11059
    Prev
    Next
    INDEX
    Explanations

    previously agreed or happened

    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
     suatu
    -0.88
    alap
    -0.88
    鎭
    -0.87
     یافت
    -0.87
    uggling
    -0.86
     作る
    -0.85
     Lakukan
    -0.84
    Currently
    -0.84
     daje
    -0.84
    ícula
    -0.84
    POSITIVE LOGITS
     earlier
    1.80
     previously
    1.75
     promised
    1.62
     ранее
    1.53
     wcześniej
    1.49
     agreed
    1.41
     tidigare
    1.36
     previous
    1.34
     previamente
    1.34
    previously
    1.32
    Activations Density 0.090%

    No Known Activations