© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83723
    Prev
    Next
    INDEX
    Explanations

    words ending in itor

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

    The neuron activates on tokens containing the substring “itor,” i.e. it detects words ending in “itor.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     were
    -2.50
    都是
    -2.28
    ка
    -2.28
     cérami
    -2.22
     営業
    -2.19
     която
    -2.17
     œufs
    -2.16
     شوید
    -2.14
    ним
    -2.13
    вод
    -2.11
    POSITIVE LOGITS
    a
    3.52
    ]
    3.47
    </i>
    2.92
    itor
    2.81
    </h3>
    2.75
    ྜ
    2.69
    ا
    2.69
    はお
    2.67
    鹇
    2.56
    则是
    2.47
    Activations Density 0.005%

    No Known Activations