© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20484
    Prev
    Next
    INDEX
    Explanations

    possessive 's and sentence structure

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

    The neuron is strongly triggered by main third-person-singular present-tense verbs (e.g. “returns,” “takes,” “has,” “finds,” “continues,” etc.) that denote the key actions in each sentence.

    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
     it
    -2.19
     this
    -2.00
     its
    -1.95
     such
    -1.79
    ).
    -1.77
     which
    -1.75
     them
    -1.70
     other
    -1.68
     including
    -1.59
     their
    -1.58
    POSITIVE LOGITS
     to
    1.90
     himself
    1.76
    óta
    1.63
    igem
    1.44
     memimpin
    1.42
    gibt
    1.37
    gefunden
    1.34
    甗
    1.34
    )];
    
    1.31
    甃
    1.31
    Activations Density 0.137%

    No Known Activations