© 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. 29180
    Prev
    Next
    INDEX
    Explanations

    anabolic steroid, government, life forms, metal-organic frameworks, habeas corpus statute, light rail station

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

    technical or specialized terminology in various domains.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to longer, multi-syllabic “content” words—especially nouns or technical terms—i.e. words that are relatively long and complex.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     that
    -1.82
     both
    -1.78
    s
    -1.66
     AppColors
    -1.65
    mathrm
    -1.56
    </h3>
    -1.56
    -1.56
    ↵↵
    -1.52
    B
    -1.48
    k
    -1.45
    POSITIVE LOGITS
    ཿ
    1.58
    buying
    1.51
     ส์
    1.46
    tieve
    1.41
     anlay
    1.41
    を選ぶ
    1.39
    
    1.38
    fillment
    1.38
    の意味
    1.37
    Zeneca
    1.37
    Activations Density 0.096%
    No Known Activations