© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73610
    Prev
    Next
    INDEX
    Explanations

    two seater

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

    The neuron fires on tokens that represent numeric data (e.g. years, counts, dates, and other digit‐containing tokens).

    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
    忽视
    -1.05
    haviours
    -1.03
    强行
    -1.02
    展现
    -1.01
     realizadas
    -1.01
     derer
    -1.00
    çons
    -1.00
    関数
    -0.99
    amico
    -0.97
    ța
    -0.97
    POSITIVE LOGITS
     expérimentés
    1.18
    érieurs
    1.09
    section
    1.05
     médicaux
    1.01
     urbaine
    1.01
     généralement
    0.95
    ndrome
    0.94
    芡
    0.94
     рассказывает
    0.94
     liebt
    0.91
    Activations Density 0.050%

    No Known Activations