© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73151
    Prev
    Next
    INDEX
    Explanations

    dates, prices, or paths

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

    The neuron is activated by numeric tokens—sequences of digits (including multi-digit numbers and decimals) wherever they occur 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_22/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
     felpa
    -1.37
     piscinas
    -1.26
     komun
    -1.23
     dipu
    -1.23
    
    -1.21
     intelek
    -1.20
     ofici
    -1.19
    alisis
    -1.16
     camisetas
    -1.16
     desn
    -1.16
    POSITIVE LOGITS
    ↵↵↵
    1.16
    N
    1.13
    ↵↵↵↵↵
    1.09
     wenigen
    1.09
    O
    1.08
    B
    1.07
    ar
    1.07
    ↵↵↵↵↵↵↵↵↵↵↵
    1.06
    L
    1.06
    S
    1.02
    Activations Density 0.011%

    No Known Activations