© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129368
    Prev
    Next
    INDEX
    Explanations

    repeal of laws

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

    The neuron consistently activates on occurrences of the word “repeal” (including its morphological variants).

    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
     {
    -3.05
     =
    -2.98
     -
    -2.84
     }
    -2.77
     \
    -2.72
     +
    -2.69
    </h4>
    -2.67
     e
    -2.63
     [
    -2.61
     и
    -2.56
    POSITIVE LOGITS
    镦
    2.95
    螄
    2.88
     protagonisti
    2.84
    ↵
    2.84
     verschill
    2.69
     車場
    2.66
     剧照
    2.59
    錾
    2.58
    銪
    2.56
    𖥦
    2.50
    Activations Density 0.002%

    No Known Activations