© 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. 11709
    Prev
    Next
    INDEX
    Explanations

    numbers and associated items

    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
     become
    -1.95
    最後に
    -1.92
    )
    -1.81
     это
    -1.74
     has
    -1.69
     positioned
    -1.67
    ↵↵
    -1.66
    —
    -1.66
     will
    -1.65
     лучших
    -1.64
    POSITIVE LOGITS
    1
    1.99
    vantaged
    1.96
     Cette
    1.93
    ciutto
    1.89
     Could
    1.83
     contiennent
    1.83
    izes
    1.80
    anément
    1.77
     Things
    1.76
     This
    1.75
    Activations Density 0.011%

    No Known Activations