© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129762
    Prev
    Next
    INDEX
    Explanations

    Melvin propulsion Creole prank asshole gastroenteritis

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

    The neuron consistently activates on occurrences of the proper name “Melvin.”

    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
    "
    -3.42
    ’
    -2.95
    あります
    -2.88
    which
    -2.84
    ↵↵
    -2.72
    you
    -2.70
    ?
    -2.45
    鱨
    -2.44
    います
    -2.30
    StoryboardSegue
    -2.30
    POSITIVE LOGITS
    ?”
    3.33
    ？”
    2.78
    撄
    2.61
    
    2.55
    
    2.31
    籀
    2.28
    佧
    2.27
    ༷
    2.23
     tidak
    2.22
    ”？
    2.20
    Activations Density 0.026%

    No Known Activations