© 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. 91103
    Prev
    Next
    INDEX
    Explanations

    correlation and association

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

    The neuron primarily detects quantitative data and measurements—i.e. numeric values (fold‐changes, counts, statistical figures) and words marking quantitative relationships.

    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
    ཀ
    -0.87
    ﻌ
    -0.84
    齑
    -0.84
    AutoScaleMode
    -0.84
     élément
    -0.83
    гона
    -0.83
    netje
    -0.82
     Ambos
    -0.81
     espa
    -0.80
    Configurator
    -0.80
    POSITIVE LOGITS
     correlation
    5.44
     correlations
    4.38
     Correlation
    4.25
    correlation
    4.22
     correlated
    4.22
     correlate
    4.09
    Correlation
    4.06
     correlates
    3.69
    correlated
    3.47
     correl
    3.45
    Activations Density 0.331%

    No Known Activations