© 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. 10-GEMMASCOPE-RES-131K
    4. 104479
    Prev
    Next
    INDEX
    Explanations

    as for or as to

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

    The neuron is looking for numeric tokens and numerical references (i.e. standalone numbers or numeric measurements) 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_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
     cuando
    -2.19
     when
    -2.16
     When
    -1.98
    when
    -1.72
     good
    -1.69
     both
    -1.66
     what
    -1.59
    iritto
    -1.59
     if
    -1.56
     has
    -1.52
    POSITIVE LOGITS
     viſ
    1.66
     ſur
    1.61
     uly
    1.60
    ᯅ
    1.60
     raiſ
    1.59
    ilets
    1.56
     effets
    1.54
     klima
    1.52
     malen
    1.52
    鲼
    1.50
    Activations Density 0.010%

    No Known Activations