© 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. 119285
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
     propOrder
    -0.80
    wali
    -0.79
    cesi
    -0.79
    ]?
    -0.78
    kerne
    -0.77
    霍
    -0.77
    احث
    -0.76
    rssi
    -0.76
    ibin
    -0.75
    Continental
    -0.75
    POSITIVE LOGITS
     numbers
    1.18
     ticket
    1.09
     tickets
    1.04
     participate
    1.03
     played
    1.02
     purchased
    1.02
     odds
    0.94
     participation
    0.94
     numéros
    0.94
     play
    0.93
    Activations Density 0.006%

    No Known Activations