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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102922
    Prev
    Next
    INDEX
    Explanations

    stratigraphy and chronology

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

    The neuron spots specialized scientific or technical terminology (especially geological and paleontological jargon).

    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
    IFS
    -0.72
    互動
    -0.69
     chạm
    -0.68
    Morfologia
    -0.68
    句
    -0.68
    cmu
    -0.67
    XY
    -0.67
     втор
    -0.66
    enger
    -0.66
     mechan
    -0.66
    POSITIVE LOGITS
     correlation
    1.41
    Correlation
    1.29
    correlation
    1.26
     chrono
    1.15
     Correlation
    1.12
     correlations
    1.08
    strat
    1.08
     correlate
    1.07
     correl
    1.07
     strat
    1.05
    Activations Density 0.013%

    No Known Activations