© 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. 128402
    Prev
    Next
    INDEX
    Explanations

    preposition of

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

    The neuron activates on gerund forms of verbs (words ending in “-ing” functioning as action nouns) used as the head of a noun phrase.

    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
    \
    -2.44
    馀
    -1.98
    鯓
    -1.81
    —
    -1.80
    🎈
    -1.79
    
    -1.69
    >
    -1.69
    er
    -1.67
    💞
    -1.65
    Noon
    -1.62
    POSITIVE LOGITS
    谖
    2.42
     ſame
    2.23
     Houſe
    2.14
     preſent
    2.11
     juſ
    2.08
    llavero
    2.03
    elser
    1.95
     sebagian
    1.95
    ING
    1.95
     unſ
    1.94
    Activations Density 0.047%

    No Known Activations