© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45573
    Prev
    Next
    INDEX
    Explanations

    machine learning algorithms

    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_34/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
     nine
    -1.05
     genuinely
    -1.00
     without
    -1.00
     fifteen
    -0.99
     seven
    -0.97
     eight
    -0.95
    osó
    -0.94
     five
    -0.93
     undoubtedly
    -0.88
     truly
    -0.87
    POSITIVE LOGITS
    lectricité
    1.05
    GEL
    0.96
    ANZA
    0.94
     colega
    0.93
    andis
    0.93
     stras
    0.93
     Dinas
    0.90
    STATION
    0.89
    (−
    0.89
    στή
    0.89
    Activations Density 0.045%

    No Known Activations