© 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. 10-GEMMASCOPE-RES-131K
    7. 104486
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    The neuron fires on numeric measurements that include a fractional part (i.e. decimal numbers like “23.75,” “50.25,” “49.75,” etc.).

    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
    ętr
    -1.55
    žiť
    -1.55
    delmi
    -1.48
     worin
    -1.46
    us
    -1.45
    ？”
    -1.45
    amb
    -1.41
    łach
    -1.41
    ach
    -1.40
     rõ
    -1.38
    POSITIVE LOGITS
     to
    2.16
     only
    1.75
    -
    1.45
     was
    1.43
    {
    1.33
    pullover
    1.31
     is
    1.26
    ਫ਼
    1.26
     provocó
    1.23
    愧
    1.23
    Activations Density 0.058%

    No Known Activations