© 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. 34-GEMMASCOPE-RES-131K
    7. 12141
    Prev
    Next
    INDEX
    Explanations

    pop prefixes

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

    The neuron fires on any appearance of the character sequence “pop” (in any context or word).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     erzielen
    -0.94
     durabilidad
    -0.78
     их
    -0.77
     успеха
    -0.77
     їх
    -0.75
     erzielt
    -0.74
    ⊰
    -0.74
    ooo
    -0.74
    Unable
    -0.74
    謂
    -0.72
    POSITIVE LOGITS
     Pop
    1.05
    팝
    0.88
    Pop
    0.85
     unpopular
    0.81
     POP
    0.81
    POP
    0.80
     pop
    0.79
     kinetics
    0.79
    ϟ
    0.78
     fär
    0.77
    Activations Density 0.019%

    No Known Activations