© 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. 84606
    Prev
    Next
    INDEX
    Explanations

    statistical relationships and correlations

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

    The neuron is strongly activated by numeric tokens (digits and numbers) and associated statistical result terms.

    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
    isEqualTo
    -0.88
    ⾞
    -0.85
    érable
    -0.81
    νονται
    -0.80
     gales
    -0.80
     дипло
    -0.79
    ΙΚ
    -0.79
    ommen
    -0.78
    hafen
    -0.78
     دی
    -0.77
    POSITIVE LOGITS
     relationship
    1.56
     positive
    1.52
     statistically
    1.45
     influence
    1.40
     significant
    1.31
     positively
    1.28
     negative
    1.25
     relationships
    1.24
     negatively
    1.22
     Significant
    1.19
    Activations Density 0.012%

    No Known Activations