© 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. 86765
    Prev
    Next
    INDEX
    Explanations

    fortune and money

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

    This neuron strongly flags uncommon “content” tokens—i.e. rarer or more informative words (nouns, adjectives, verbs, numbers, etc.) rather than high-frequency function words.

    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
    🚒
    -0.85
    ☕
    -0.83
    🧹
    -0.82
    onTap
    -0.81
     cabos
    -0.81
    Bishop
    -0.80
    kosten
    -0.80
     verst
    -0.79
    Anxiety
    -0.78
    🍳
    -0.78
    POSITIVE LOGITS
     luck
    1.48
     fortune
    1.44
    fortune
    1.23
     fortunes
    1.10
     Fortune
    1.07
    Fortune
    1.02
     peach
    0.98
     Luck
    0.96
     money
    0.96
     lucky
    0.95
    Activations Density 0.001%

    No Known Activations