© 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. 19464
    Prev
    Next
    INDEX
    Explanations

    proper nouns or beginnings of terms

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

    The neuron fires on French indirect‐object pronouns (e.g. “lui,” “leur”).

    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
    ↵↵
    -2.84
    )$
    -2.58
     meisten
    -2.39
    -2.33
     günstiger
    -2.22
    -2.20
    我没有
    -2.16
    },
    -2.13
     gewerb
    -2.13
     []
    -2.08
    POSITIVE LOGITS
    
    2.78
    薷
    2.72
    
    2.58
     restent
    2.48
     ……
    2.45
    
    2.42
    癀
    2.36
     promove
    2.36
     seraient
    2.34
    埽
    2.30
    Activations Density 0.000%

    No Known Activations