© 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. 42843
    Prev
    Next
    INDEX
    Explanations

    prefrontal cortex

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

    regions of the brain, especially "prefrontal cortex" and related brain structures.

    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
    过去的
    -1.80
    ρες
    -1.68
    眼下
    -1.63
    目前的
    -1.54
    êts
    -1.52
     использованием
    -1.52
    arashtra
    -1.51
     ?,
    -1.50
    。"
    -1.50
     rencontr
    -1.49
    POSITIVE LOGITS
    there
    1.80
    ↵
    1.70
    however
    1.66
     same
    1.53
    {
    1.47
    ло
    1.45
     there
    1.38
     次元
    1.37
     about
    1.34
     somewhat
    1.31
    Activations Density 0.017%

    No Known Activations