© 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. 7428
    Prev
    Next
    INDEX
    Explanations

    action to alter a situation

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

    The neuron activates on mentions of “intervene” and its variants (e.g. intervention, intervened, intervening).

    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
    '
    -2.91
    ’
    -2.00
    €™
    -1.76
     accompanying
    -1.64
     parcs
    -1.61
     connection
    -1.61
     irgende
    -1.59
    ى
    -1.58
     практике
    -1.57
    一张
    -1.55
    POSITIVE LOGITS
    s
    1.93
    锜
    1.85
    ❉
    1.83
    喾
    1.77
    婳
    1.73
    潆
    1.73
     Одна
    1.72
    措施
    1.70
    </sup>
    1.70
     Şubat
    1.69
    Activations Density 0.017%

    No Known Activations