© 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. 40922
    Prev
    Next
    INDEX
    Explanations

    born on

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

    The neuron strongly activates on commas that separate date components (e.g. day, month, and year) in biographical date strings.

    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
     entire
    -1.80
     different
    -1.73
    之际
    -1.73
    their
    -1.72
    THERE
    -1.68
     time
    -1.67
     specifics
    -1.67
     particular
    -1.65
    They
    -1.65
    they
    -1.63
    POSITIVE LOGITS
    桄
    1.71
    strijden
    1.49
    Ꮞ
    1.48
    </b>
    1.47
    ності
    1.41
    </h5>
    1.41
     lingkungan
    1.38
    każ
    1.38
    CodeAttribute
    1.37
    рения
    1.37
    Activations Density 0.063%

    No Known Activations