© 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. 59919
    Prev
    Next
    INDEX
    Explanations

    xhtml and UnitTesting

    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
     just
    -0.94
     both
    -0.91
     over
    -0.86
     superbly
    -0.83
     cleverly
    -0.83
     ironically
    -0.82
     supremely
    -0.81
    糧
    -0.81
     all
    -0.81
     unparalleled
    -0.81
    POSITIVE LOGITS
     encaje
    0.92
    När
    0.91
     hué
    0.91
    люми
    0.91
    går
    0.91
     WHEN
    0.90
     rozum
    0.90
    FFE
    0.90
     princípios
    0.88
    isst
    0.87
    Activations Density 0.001%

    No Known Activations