© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67820
    Prev
    Next
    INDEX
    Explanations

    person's birth and death years

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

    The neuron detects four-digit year numbers (dates).

    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
    íba
    -1.41
     JAKARTA
    -1.41
    歘
    -1.39
     endom
    -1.35
     vanil
    -1.34
     demor
    -1.27
    呪術
    -1.25
     bruno
    -1.24
     melat
    -1.23
     garcia
    -1.23
    POSITIVE LOGITS
    boleh
    1.42
    uidado
    1.39
     other
    1.35
     Gehäuse
    1.29
     parfü
    1.29
     ähnlich
    1.28
     koszt
    1.28
    jadikan
    1.27
     for
    1.25
     muelle
    1.25
    Activations Density 0.037%

    No Known Activations