© 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. 10978
    Prev
    Next
    INDEX
    Explanations

    states and their consequences

    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
    这些
    -0.95
    Джерело
    -0.91
    これは
    -0.90
     amelyek
    -0.90
    likation
    -0.89
    Ранее
    -0.86
    Класси
    -0.85
     після
    -0.84
    dities
    -0.84
     amerik
    -0.83
    POSITIVE LOGITS
     then
    1.16
     help
    1.05
    使
    0.96
     permettant
    0.90
     purpose
    0.90
     gebruikt
    0.88
     gefahren
    0.86
     reflected
    0.85
     davor
    0.85
     أعلام
    0.84
    Activations Density 0.140%

    No Known Activations