© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111526
    Prev
    Next
    INDEX
    Explanations

    Adam's question

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

    The neuron detects individual digits and numerical constants (i.e. characters or tokens representing 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_10/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
     Fällen
    -1.61
     ganzes
    -1.49
     všechny
    -1.48
     the
    -1.46
    訁
    -1.43
    chsel
    -1.37
    玙
    -1.37
    :
    -1.36
     everything
    -1.35
     dergleichen
    -1.35
    POSITIVE LOGITS
     if
    1.64
    \
    1.46
     These
    1.45
     Unlike
    1.45
     also
    1.41
    。
    1.41
     there
    1.41
    服用
    1.38
    糖尿病
    1.36
    Награ
    1.35
    Activations Density 0.005%

    No Known Activations