© 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. 33754
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by the

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

    The neuron activates on tokens forming date expressions—numbers (days, years) and month names.

    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
     a
    -1.02
    每一
    -0.88
    を教えて
    -0.83
    related
    -0.82
    下車
    -0.82
     physical
    -0.77
    であるが
    -0.77
     related
    -0.74
     każdej
    -0.74
    というのが
    -0.73
    POSITIVE LOGITS
     the
    2.72
    第
    0.95
    🔈
    0.92
    OnThe
    0.91
    ALLY
    0.89
    chafft
    0.83
    雑誌
    0.82
     Polisi
    0.81
    SPONS
    0.80
     klara
    0.80
    Activations Density 0.057%

    No Known Activations