© 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. 7027
    Prev
    Next
    INDEX
    Explanations

    advancements

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

    The neuron fires on occurrences of the word “advancement” or “advancements,” highlighting mentions of progress or new developments.

    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
    睒
    -2.75
     ());
    -2.39
     prioriti
    -2.34
    -2.25
    💜
    -2.22
    💪
    -2.14
    🤍
    -2.14
     ]}
    -2.13
     館
    -2.13
    🖤
    -2.11
    POSITIVE LOGITS
    ↵
    3.34
    ’
    3.02
    他们的
    2.88
    攙
    2.84
    蛱
    2.81
     "
    2.73
    氿
    2.69
    their
    2.44
    
    2.36
    𐄁
    2.33
    Activations Density 0.004%

    No Known Activations