© 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. 118349
    Prev
    Next
    INDEX
    Explanations

    quality and build

    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
    facade
    -0.85
     tā
    -0.83
    Mathematics
    -0.79
    spania
    -0.79
    chada
    -0.79
     Familie
    -0.75
     exitosa
    -0.75
     Wahrheit
    -0.74
    sef
    -0.74
     votre
    -0.74
    POSITIVE LOGITS
     quality
    2.69
     construction
    2.48
     workmanship
    2.16
     solidly
    1.93
    质量
    1.93
     sturdy
    1.91
     Quality
    1.88
     build
    1.88
    Quality
    1.88
    quality
    1.88
    Activations Density 0.037%

    No Known Activations