© 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. 298
    Prev
    Next
    INDEX
    Explanations

    dates and deadlines

    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
     was
    -0.94
     culin
    -0.93
     pomer
    -0.91
     is
    -0.89
    뉘
    -0.88
    Elk
    -0.88
    बस
    -0.86
     mentira
    -0.85
     BRING
    -0.85
    ovat
    -0.84
    POSITIVE LOGITS
     if
    1.66
     any
    1.43
     to
    1.20
     если
    1.13
     If
    1.09
     để
    1.09
     either
    1.08
    Any
    1.07
    because
    1.05
     Any
    1.02
    Activations Density 0.012%

    No Known Activations