© 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. 10-GEMMASCOPE-RES-131K
    7. 104117
    Prev
    Next
    INDEX
    Explanations

    likely to be

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

    The neuron responds to hedging language—especially the word “likely” (and similar markers of probability).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    岨
    -2.23
    喾
    -2.20
     Technically
    -2.14
    ”
    -2.03
    ჻
    -1.99
     Most
    -1.85
     we
    -1.82
     видом
    -1.81
    getJSONArray
    -1.81
    榈
    -1.77
    POSITIVE LOGITS
     be
    2.47
     tohto
    2.03
    ỽ
    1.99
    皤
    1.95
    齜
    1.86
    wakili
    1.80
    纡
    1.80
     zelfs
    1.77
    塤
    1.77
    
    1.74
    Activations Density 0.009%

    No Known Activations