© 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. 55776
    Prev
    Next
    INDEX
    Explanations

    years in the 1800s

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

    The neuron spots numeric year references (four-digit dates) in the text.

    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
     well
    -2.64
    Well
    -2.38
     Well
    -2.11
    well
    -1.97
     WELL
    -1.76
     dobře
    -1.55
     dobrze
    -1.55
    WELL
    -1.48
     хорошо
    -1.41
     wells
    -1.37
    POSITIVE LOGITS
     when
    1.45
     When
    1.20
     improve
    1.17
    3
    1.16
    4
    1.14
    5
    1.05
    0
    1.04
    7
    1.04
    2
    1.03
    8
    1.03
    Activations Density 0.045%

    No Known Activations