© 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. 104942
    Prev
    Next
    INDEX
    Explanations

    drop verb

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

    This neuron fires on occurrences of the verb “drop” (including its inflected forms like “dropping,” “dropped,” etc.).

    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
     deserto
    -2.02
     pulsante
    -1.96
    >
    -1.96
     pousada
    -1.96
     rafael
    -1.91
     这个
    -1.90
     rodrigo
    -1.87
    on
    -1.86
     bougies
    -1.85
     sentra
    -1.81
    POSITIVE LOGITS
    ’
    2.22
     мы
    2.17
     notre
    2.17
    身边的
    2.05
    涑
    1.87
     into
    1.84
    wakili
    1.82
    </i>
    1.81
    皱眉
    1.78
     целью
    1.77
    Activations Density 0.015%

    No Known Activations