© 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. 22-GEMMASCOPE-RES-131K
    7. 27067
    Prev
    Next
    INDEX
    Explanations

    born followed by location or date

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

    This neuron detects four-digit year numbers (e.g. birth years) in biographical entries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     now
    -1.60
     this
    -1.56
     it
    -1.40
     each
    -1.40
     which
    -1.31
    کنون
    -1.15
     will
    -1.13
    anyeol
    -1.05
     such
    -1.03
    ệu
    -0.98
    POSITIVE LOGITS
     born
    1.25
    unächst
    1.16
     decorativo
    1.13
     nació
    1.11
     бъ
    1.10
     pán
    1.09
     meste
    1.08
     evangé
    1.08
    klik
    1.05
     ailes
    1.05
    Activations Density 0.114%

    No Known Activations