© 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. 34-GEMMASCOPE-RES-131K
    7. 93363
    Prev
    Next
    INDEX
    Explanations

    birth year formatting

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

    This neuron specializes in spotting numeric date and year information (e.g. birth years, dates) in biographical 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
    ٽ
    -1.00
    これも
    -0.95
    rú
    -0.88
     unbelievable
    -0.88
     if
    -0.86
    教科
    -0.85
    Manfaat
    -0.85
    山形
    -0.84
    Belfast
    -0.84
     میر
    -0.84
    POSITIVE LOGITS
     nearby
    1.04
     zondag
    1.04
    ビックリ
    1.04
     sufrir
    1.03
     Lower
    1.01
    ほら
    1.01
    ]{\
    0.99
     East
    0.98
    𖧵
    0.98
     anún
    0.97
    Activations Density 0.089%

    No Known Activations