© 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. 22-GEMMASCOPE-RES-131K
    7. 10999
    Prev
    Next
    INDEX
    Explanations

    luckily, fortunately, enough

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

    This neuron detects adverbs expressing relief or good fortune (e.g. “fortunately,” “luckily,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     regels
    -1.03
     gezicht
    -0.98
    ákat
    -0.96
     collectie
    -0.92
     intentar
    -0.89
     waard
    -0.88
     maanden
    -0.87
     acabo
    -0.87
    oosevelt
    -0.85
     moeili
    -0.85
    POSITIVE LOGITS
     enough
    1.54
     luckily
    1.30
     able
    1.30
     fortunately
    1.23
    Luckily
    1.20
     suffisamment
    1.18
     otherwise
    1.17
     luck
    1.08
    enough
    1.06
     sufficient
    1.03
    Activations Density 0.024%

    No Known Activations