© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67403
    Prev
    Next
    INDEX
    Explanations

    repression, repressed, repress

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

    The neuron activates on words built from the “repress” root (e.g. repress, repressed, repression, repressing).

    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
    '
    -2.83
    锻
    -2.44
    enablog
    -2.42
     the
    -2.38
    蚨
    -2.27
    \
    -2.23
     recognize
    -2.13
                
    -2.09
     participate
    -2.06
     recommend
    -2.02
    POSITIVE LOGITS
    ↵
    2.59
    0
    2.45
     Tentang
    2.17
    ’
    2.14
    ቍ
    2.09
    ﱠ
    2.03
    Применение
    1.95
    滏
    1.94
    y
    1.94
     Bagaimana
    1.92
    Activations Density 0.004%

    No Known Activations