© 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. 15477
    Prev
    Next
    INDEX
    Explanations

    CDP, Zeppelin, Tsar, IDR, Tzu

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

    The neuron strongly activates on uppercase or title‐cased named entities (proper names and acronyms).

    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
    b
    -2.98
    x
    -2.91
    p
    -2.83
    崀
    -2.72
    或者
    -2.50
    8
    -2.50
    6
    -2.48
    vous
    -2.42
     телефона
    -2.39
     یا
    -2.38
    POSITIVE LOGITS
    棪
    2.86
     It
    2.84
     był
    2.67
    𖥧
    2.30
    
    2.25
    ⸒
    2.23
    錞
    2.23
     But
    2.23
    囖
    2.22
    酲
    2.20
    Activations Density 0.057%

    No Known Activations