© 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. 10-GEMMASCOPE-RES-131K
    7. 28956
    Prev
    Next
    INDEX
    Explanations

    ischemic stroke refugees

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

    surnames like Friedman, Duffy, Syrian, and terms related to ischemic conditions.

    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_10/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
    n
    -3.52
    o
    -3.44
    h
    -3.39
    ↵
    -3.28
    z
    -3.03
    ↵↵
    -3.03
    i
    -2.94
    j
    -2.94
    l
    -2.83
    ll
    -2.73
    POSITIVE LOGITS
     dezelve
    2.78
    辚
    2.59
    鮰
    2.52
    驺
    2.52
    罍
    2.52
    戗
    2.42
    
    2.38
     restoran
    2.34
    𝄆
    2.33
    ﹶ
    2.33
    Activations Density 0.012%

    No Known Activations