© 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. 47465
    Prev
    Next
    INDEX
    Explanations

    the word one

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

    This neuron detects uses of the singular pronoun “one” (e.g. “the one,” “a new one,” “the old one”) referring back to a previously mentioned item or version.

    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
    的
    -2.28
    .....
    -2.02
    ......
    -2.02
     nimmer
    -2.02
     gebeten
    -2.00
    ,'
    -1.98
    5
    -1.92
    :
    -1.91
     '
    -1.91
    7
    -1.91
    POSITIVE LOGITS
     It
    3.84
     Another
    2.42
     它
    1.99
    塤
    1.98
     This
    1.96
     aprender
    1.90
     estaremos
    1.90
     ersten
    1.89
    +}\
    1.89
    をも
    1.88
    Activations Density 0.015%

    No Known Activations