© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26063
    Prev
    Next
    INDEX
    Explanations

    modes of inquiry, mind, code, people, wealth, technologies, keywords, storing

    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
    摸了
    -1.42
    ༷
    -1.31
    
    -1.31
     pareti
    -1.30
    などを
    -1.30
    下意识
    -1.30
    点点头
    -1.30
    鼋
    -1.27
     degrés
    -1.27
     köy
    -1.26
    POSITIVE LOGITS
     activities
    1.62
     which
    1.55
     helps
    1.54
     doing
    1.50
     when
    1.49
     Usually
    1.45
     people
    1.38
     During
    1.37
     exquisite
    1.36
    jenigen
    1.36
    Activations Density 0.060%

    No Known Activations