© 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. 34-GEMMASCOPE-RES-131K
    7. 111063
    Prev
    Next
    INDEX
    Explanations

    4 followed by 3 or 4

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

    The neuron activates on four-digit numeric tokens (e.g. years, page or section numbers).

    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
    gardens
    -0.96
    ppen
    -0.90
    formatics
    -0.86
     СО
    -0.85
    اتور
    -0.85
    脑子
    -0.84
     rámci
    -0.84
    👍👍
    -0.84
    omo
    -0.84
     ibunya
    -0.82
    POSITIVE LOGITS
     horsemen
    0.77
    coder
    0.73
    PARTMENT
    0.72
     pursu
    0.70
    留言
    0.68
    钢
    0.68
     Heu
    0.68
     insbesondere
    0.68
     Ume
    0.67
     veldig
    0.67
    Activations Density 0.109%

    No Known Activations