© 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. 41092
    Prev
    Next
    INDEX
    Explanations

    Griffin, Barrett, Connor, Gazette

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

    The neuron specifically fires on the surname “Griffin” (and close variants) whenever it appears as a standalone proper name.

    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
    {
    -3.44
     Utilize
    -2.95
     Ensuring
    -2.61
    𓆜
    -2.45
    
    -2.45
     Practically
    -2.38
    )
    -2.31
     same
    -2.30
     Erlebn
    -2.27
    M
    -2.25
    POSITIVE LOGITS
    峩
    2.77
    ’，
    2.48
    σης
    2.41
     был
    2.36
    '
    2.30
    鏨
    2.25
    
    2.23
    也可以
    2.22
    ;
    2.22
    縂
    2.17
    Activations Density 0.005%

    No Known Activations