© 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. 59048
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

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

    The neuron triggers on standalone numeric tokens (e.g. years, post counts, IDs, large 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
    解码
    -0.68
     Brod
    -0.67
    を生
    -0.66
    羰
    -0.66
    udy
    -0.66
    習
    -0.65
     OCLC
    -0.64
     实例
    -0.63
     herring
    -0.63
     갈
    -0.63
    POSITIVE LOGITS
    ური
    0.76
     SCS
    0.75
    sector
    0.74
     Split
    0.73
     confiscation
    0.72
     गण
    0.72
    OME
    0.72
     Ducati
    0.71
     argon
    0.71
    dicos
    0.70
    Activations Density 0.026%

    No Known Activations