© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40767
    Prev
    Next
    INDEX
    Explanations

    yesterday

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

    The neuron detects the word “yesterday” (and its foreign‐language equivalents like “včera” or “ontem”) marking a reference to the previous day.

    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
    ︓
    -1.52
    晛
    -1.48
    anguardia
    -1.45
    躂
    -1.45
     with
    -1.44
    衎
    -1.44
     magnético
    -1.41
    وانید
    -1.41
     vince
    -1.39
    掮
    -1.38
    POSITIVE LOGITS
     posibles
    1.66
     względem
    1.50
     esencial
    1.45
    好在
    1.45
    2
    1.43
     haces
    1.42
     seleccion
    1.38
    
    1.36
    骉
    1.34
    
    1.33
    Activations Density 0.075%

    No Known Activations