© 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. 80827
    Prev
    Next
    INDEX
    Explanations

    pop up

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

    The neuron activates whenever it encounters the verb “pop” in its various inflected forms (pop, pops, popped, popping).

    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
     putea
    -1.02
     trebui
    -0.92
     lepro
    -0.85
    chiede
    -0.83
     coming
    -0.82
    coming
    -0.81
    乜
    -0.81
    IMAN
    -0.79
    otations
    -0.79
    uments
    -0.78
    POSITIVE LOGITS
     popping
    1.77
     pop
    1.66
     out
    1.61
     pops
    1.60
     popped
    1.55
     POP
    1.41
     into
    1.39
    pop
    1.31
     Pop
    1.31
    pops
    1.24
    Activations Density 0.012%

    No Known Activations