© 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. 117854
    Prev
    Next
    INDEX
    Explanations

    Japanese sakura, cherry, and fruit trees

    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
    夏休み
    -0.79
    zember
    -0.78
    ัตว์
    -0.77
    summer
    -0.76
     Laguna
    -0.75
    скоре
    -0.75
     vegetables
    -0.75
    spin
    -0.75
     kelp
    -0.75
    iacute
    -0.74
    POSITIVE LOGITS
    🌸
    1.27
     trees
    1.27
     pink
    1.23
     🌸
    1.20
    sakura
    1.17
     cherry
    1.16
     bloom
    1.10
     petals
    1.10
     Cherry
    1.09
     blossom
    1.09
    Activations Density 0.012%

    No Known Activations