© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90674
    Prev
    Next
    INDEX
    Explanations

    on pace, on track, on schedule

    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
     garantías
    -1.55
    檍
    -1.52
    埽
    -1.49
    传来
    -1.48
    AutoresizingMask
    -1.48
     écout
    -1.44
     hinzufügen
    -1.37
    犼
    -1.35
    otriz
    -1.35
     deportes
    -1.35
    POSITIVE LOGITS
     for
    1.67
    '
    1.59
     '
    1.38
     üzere
    1.33
    ↵
    1.27
    '})
    1.23
     
    1.20
    !
    1.20
     miljoen
    1.18
     We
    1.16
    Activations Density 0.025%

    No Known Activations