© 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. 98816
    Prev
    Next
    INDEX
    Explanations

    I thought it was

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

    The neuron responds to numeric tokens (numbers or measurements) in the text.

    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
     не
    -1.77
    渃
    -1.67
    became
    -1.63
    鯧
    -1.62
     получили
    -1.62
    ooooo
    -1.57
     Belgien
    -1.57
    abaikan
    -1.56
    〼
    -1.54
     offerte
    -1.52
    POSITIVE LOGITS
    {
    1.55
    },
    1.44
     LEAST
    1.40
    惟
    1.39
     maybe
    1.38
    ali
    1.36
    ようになる
    1.36
     ta
    1.35
    ],
    1.33
     碗
    1.31
    Activations Density 0.017%

    No Known Activations