© 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. 123690
    Prev
    Next
    INDEX
    Explanations

    hepatotoxicity, toxins, poisoning

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

    The neuron detects the term "hepato" or related liver toxicity terminology.

    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
    澈
    -2.73
    cazione
    -2.66
    鲠
    -2.56
    pecabe
    -2.55
    
    -2.53
     These
    -2.48
    樨
    -2.47
    阏
    -2.39
    founders
    -2.39
    NOWLEDGE
    -2.39
    POSITIVE LOGITS
    ato
    3.89
    “
    3.34
    焄
    2.95
    ↵↵
    2.86
    -
    2.63
    ?
    2.53
    سبة
    2.42
    1
    2.41
    あんまり
    2.34
    _
    2.34
    Activations Density 0.008%

    No Known Activations