© 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. 104733
    Prev
    Next
    INDEX
    Explanations

    transferring or flipping something

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

    The neuron specifically fires on the word “over” when it appears as part of a phrasal verb (e.g. “turn over,” “hand over,” “giving over”) indicating transfer or completion of an action.

    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
    -2.95
    9
    -2.83
    7
    -2.69
    _
    -2.58
    5
    -2.50
    8
    -2.50
    4
    -2.44
    2
    -2.34
    6
    -2.17
    "
    -2.14
    POSITIVE LOGITS
     italianos
    1.87
     habido
    1.84
     diputados
    1.83
    ⑉
    1.80
     directivos
    1.80
     cubanos
    1.80
    ángulo
    1.80
     to
    1.78
     bonos
    1.77
     distritos
    1.77
    Activations Density 0.003%

    No Known Activations