© 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. 111626
    Prev
    Next
    INDEX
    Explanations

    born in or on

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

    The neuron fires on numeric tokens that occur in date or age expressions (birth/death years, dates, ages).

    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
     μας
    -1.27
    каде
    -1.18
    ༴
    -1.15
     их
    -1.15
    ヌーピー
    -1.13
     Setiap
    -1.12
    อีก
    -1.11
    revet
    -1.09
    Universität
    -1.09
     système
    -1.09
    POSITIVE LOGITS
     that
    1.20
     cráneo
    1.20
     育
    1.18
     part
    1.15
     normalerweise
    1.13
     fija
    1.11
     parts
    1.10
     pouze
    1.08
     vẫn
    1.07
    OLOGIA
    1.07
    Activations Density 0.105%

    No Known Activations