© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72387
    Prev
    Next
    INDEX
    Explanations

    to + verb

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

    The neuron strongly responds to transitive action verbs (i.e. verbs that describe doing something to an object).

    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
    e
    -2.50
    吶
    -1.99
    後面
    -1.71
    璈
    -1.68
    赑
    -1.67
    睒
    -1.63
    花费
    -1.62
    附近的
    -1.61
    セッション
    -1.59
     blocco
    -1.59
    POSITIVE LOGITS
    }
    1.98
    饹
    1.86
     sabias
    1.86
     sabia
    1.80
     *,
    1.73
     amorosa
    1.70
     хотел
    1.67
    но
    1.66
    ations
    1.66
    ۹
    1.66
    Activations Density 0.008%

    No Known Activations