© 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. 15749
    Prev
    Next
    INDEX
    Explanations

    proved to be effective

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

    The neuron specifically fires on occurrences of the word “proved.”

    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
    臜
    -2.44
    ⬮
    -2.33
    蠃
    -2.23
    ꨄ
    -2.19
    驀
    -2.17
    ⛦
    -2.17
    ⵌ
    -2.17
     был
    -2.11
    sekten
    -2.09
     入荷
    -2.08
    POSITIVE LOGITS
    ’
    3.09
    t
    3.06
     Another
    2.67
     Luckily
    2.39
     parecia
    2.31
     However
    2.30
     Similarly
    2.30
     proved
    2.28
     Other
    2.28
     Selecting
    2.27
    Activations Density 0.003%

    No Known Activations