© 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. 22-GEMMASCOPE-RES-131K
    7. 95352
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    content displayed in a specific column or vertical position in text formatting.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     empezar
    -1.05
     this
    -0.99
     beginning
    -0.97
     first
    -0.90
    Alexis
    -0.89
    ͂
    -0.89
    indahan
    -0.89
    spill
    -0.86
    ต่อไป
    -0.84
    korb
    -0.84
    POSITIVE LOGITS
    を
    0.90
     '&#
    0.83
     benzina
    0.80
     jednak
    0.80
     vicar
    0.79
     บาง
    0.79
    entino
    0.79
     dintre
    0.77
     scallops
    0.77
    娶
    0.76
    Activations Density 0.000%

    No Known Activations