© 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. 97946
    Prev
    Next
    INDEX
    Explanations

    Cypress Park merging

    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
    (({
    -0.88
    絆
    -0.82
    ンド
    -0.80
     Finalmente
    -0.80
     eikä
    -0.79
     circumference
    -0.78
     rumbo
    -0.75
    прав
    -0.75
    तः
    -0.75
    (',
    -0.74
    POSITIVE LOGITS
     merged
    1.02
    Merge
    0.98
     merging
    0.98
    merge
    0.96
    arraycopy
    0.93
     срав
    0.90
     merge
    0.89
    合并
    0.88
    Merged
    0.84
     Merge
    0.82
    Activations Density 0.008%

    No Known Activations