© 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. 11080
    Prev
    Next
    INDEX
    Explanations

    synuclein, Jenkins, club, acid

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

    This neuron activates on specific named entities including protein names (like "synuclein"), software names (like "Jenkins"), person names (like "Tebow"), and other named entities.

    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
    ovací
    -1.46
     hiasan
    -1.45
     chén
    -1.44
     Ponder
    -1.43
     presenza
    -1.43
     feier
    -1.41
     Pág
    -1.40
     fliegen
    -1.38
     veliko
    -1.37
    höhung
    -1.36
    POSITIVE LOGITS
     STILL
    1.82
     come
    1.58
     been
    1.55
     送
    1.48
    zości
    1.45
     市场
    1.43
    ]
    1.42
     остались
    1.40
     και
    1.39
     kommen
    1.39
    Activations Density 0.037%

    No Known Activations