© 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. 22-GEMMASCOPE-RES-131K
    7. 9767
    Prev
    Next
    INDEX
    Explanations

    code context

    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
     These
    -0.97
     соответственно
    -0.91
     perdagangan
    -0.87
     专业
    -0.84
     or
    -0.83
    CollectionUtils
    -0.83
     as
    -0.82
     均
    -0.81
     anstatt
    -0.80
     There
    -0.79
    POSITIVE LOGITS
    atized
    1.15
    写真は
    1.08
     ressemble
    1.07
     Transfermarkt
    1.00
     цьому
    0.98
    などが
    0.97
    sistence
    0.97
    managed
    0.96
     воспользова
    0.94
    걍
    0.94
    Activations Density 0.001%

    No Known Activations