© 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. 34-GEMMASCOPE-RES-131K
    7. 59481
    Prev
    Next
    INDEX
    Explanations

    Southern states and slavery

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

    The neuron primarily activates on numeric tokens—years, dates, counts, and other numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     superfí
    -0.85
     courriel
    -0.84
     公主
    -0.84
    ジタル
    -0.82
    &)
    -0.81
    のおすすめ
    -0.80
     besieged
    -0.79
     aktiven
    -0.79
    /*/
    -0.79
     Gorb
    -0.79
    POSITIVE LOGITS
     Southern
    2.20
    Southern
    1.89
     southern
    1.73
     white
    1.64
     planters
    1.47
     South
    1.44
     cotton
    1.42
     slavery
    1.41
     planter
    1.41
     plantation
    1.40
    Activations Density 0.020%

    No Known Activations