© 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. 34726
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical concepts

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

    The neuron primarily detects and responds to numeric tokens (numbers and digits) in the text.

    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
    唯有
    -0.81
     Feng
    -0.72
    NULL
    -0.71
     selaku
    -0.70
     phòng
    -0.70
     доб
    -0.69
    engagent
    -0.68
     SCIENCES
    -0.68
    指向
    -0.68
     Options
    -0.68
    POSITIVE LOGITS
    ící
    0.87
    OuterAlt
    0.82
    Lecturer
    0.79
    헴
    0.77
    opheles
    0.77
    BIDDEN
    0.77
     cluster
    0.76
    apture
    0.74
     climá
    0.70
     universitaria
    0.70
    Activations Density 0.012%

    No Known Activations