© 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. 22-GEMMASCOPE-RES-131K
    4. 93414
    Prev
    Next
    INDEX
    Explanations

    code tokens and symbols

    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
     this
    -1.06
     Use
    -1.05
     Öff
    -1.05
     ensure
    -1.05
     This
    -0.99
     leistungs
    -0.96
    itsub
    -0.95
     using
    -0.94
     Many
    -0.93
     information
    -0.92
    POSITIVE LOGITS
     capot
    1.04
    oltán
    1.03
     Rusi
    1.02
     terape
    1.02
     même
    1.02
     organik
    1.01
    槼
    1.01
     tene
    1.01
     kutu
    1.01
     patria
    0.99
    Activations Density 0.002%

    No Known Activations