© 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. 61198
    Prev
    Next
    INDEX
    Explanations

    homeostatic

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

    The neuron detects the word "home" in various contexts including addresses, websites, and technical terms.

    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
    '
    -2.36
     
    -2.33
     сдела
    -2.33
    }
    -2.30
    すごく
    -2.22
    </h3>
    -2.22
    鮋
    -2.20
     "
    -2.17
    bringung
    -2.17
     характеристи
    -2.13
    POSITIVE LOGITS
    鸯
    3.09
    灕
    2.67
    附近的
    2.63
    呓
    2.61
     theses
    2.56
    Aunque
    2.55
    月下
    2.50
    Luego
    2.45
    También
    2.45
    Estos
    2.44
    Activations Density 0.035%

    No Known Activations