© 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. 47561
    Prev
    Next
    INDEX
    Explanations

    1, 2, 's', 't'

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

    The neuron specializes in detecting numeric tokens (numbers, dates, and other digit sequences) 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
     S
    -1.66
     In
    -1.65
     three
    -1.63
     If
    -1.63
     relatively
    -1.59
     T
    -1.58
     When
    -1.55
     for
    -1.53
     >
    -1.51
     J
    -1.48
    POSITIVE LOGITS
    
    1.84
    媄
    1.76
    〮
    1.70
    曁
    1.66
     tranſ
    1.65
     rigue
    1.63
    nál
    1.59
     ſtre
    1.59
    และ
    1.58
    nél
    1.57
    Activations Density 0.078%

    No Known Activations