© 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. 90516
    Prev
    Next
    INDEX
    Explanations

    Cleveland Browns and Twitter

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

    The neuron consistently lights up on any token containing digits (i.e. numeric strings, IDs, version or year numbers).

    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
     into
    -0.77
    aliere
    -0.73
     krę
    -0.71
     Apfel
    -0.70
    Haut
    -0.68
    excellents
    -0.68
     preescolar
    -0.68
    加藤
    -0.67
    desliz
    -0.67
     ensue
    -0.66
    POSITIVE LOGITS
    lang
    1.09
     text
    1.07
     Entities
    1.03
    Entities
    1.00
     tweet
    0.96
    User
    0.94
    text
    0.91
     scrubber
    0.90
    Text
    0.90
    entities
    0.90
    Activations Density 0.009%

    No Known Activations