© 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. 131007
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on clock‐style time expressions (e.g. “12:38 PM”)—numbers surrounding a colon followed by “AM” or “PM.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    math expressions and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     after
    -0.89
    
    -0.86
    LikeLiked
    -0.86
     जो
    -0.81
     deductions
    -0.80
    Ỵ
    -0.77
     variation
    -0.77
    ():
    -0.76
    ctuaries
    -0.76
     courthouse
    -0.75
    POSITIVE LOGITS
     nouveautés
    0.88
     thì
    0.84
     вернуть
    0.82
    gives
    0.81
     ícone
    0.80
     equipamento
    0.80
    ULAN
    0.78
     الخاصة
    0.78
     depres
    0.78
     imóvel
    0.77
    Activations Density 0.057%

    No Known Activations