© 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. 34-GEMMASCOPE-RES-131K
    4. 83797
    Prev
    Next
    INDEX
    Explanations

    code configuration properties

    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
     stycznia
    -0.93
    colata
    -0.87
     būtų
    -0.85
     harps
    -0.85
    ǽ
    -0.84
    ícias
    -0.83
     समान
    -0.82
     unparalleled
    -0.81
     Boven
    -0.80
    ędzynarod
    -0.80
    POSITIVE LOGITS
     siguientes
    0.84
    がありますが
    0.84
     предоставля
    0.83
     tía
    0.83
    ..(
    0.82
     reivindic
    0.82
     inoxidable
    0.81
    扮演
    0.80
     tirada
    0.79
    Vezi
    0.78
    Activations Density 0.019%

    No Known Activations