© 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. 55774
    Prev
    Next
    INDEX
    Explanations

    parenthetical usage

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

    This neuron detects numeric tokens (sequences of 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
    Để
    -0.80
    侖
    -0.80
     között
    -0.78
    识
    -0.76
    修改
    -0.76
     karyawan
    -0.73
    紧接着
    -0.73
    defined
    -0.73
     ਦੀ
    -0.72
    added
    -0.71
    POSITIVE LOGITS
    ances
    1.06
     remote
    0.85
    actable
    0.81
     remota
    0.80
    encrypted
    0.79
    cached
    0.78
     withdrawal
    0.77
    integer
    0.77
    ısını
    0.75
     surveillance
    0.75
    Activations Density 0.018%

    No Known Activations