© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37926
    Prev
    Next
    INDEX
    Explanations

    legal docket numbers

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

    The neuron is simply detecting numeric tokens (and outputting their numeric value as its activation).

    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
    yce
    -0.79
    讥
    -0.73
     الوس
    -0.73
    ListBy
    -0.71
     MDC
    -0.68
    adr
    -0.68
    Tug
    -0.68
    usu
    -0.67
     camb
    -0.67
     Wij
    -0.67
    POSITIVE LOGITS
     relativistic
    0.72
    Khach
    0.71
     legislation
    0.70
     sexism
    0.69
    してみると
    0.67
    ímica
    0.66
    匾
    0.66
    膳
    0.66
    腾讯
    0.66
     trăm
    0.66
    Activations Density 0.076%

    No Known Activations