© 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. 22-GEMMASCOPE-RES-131K
    7. 69187
    Prev
    Next
    INDEX
    Explanations

    mathematical problem statements

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

    The neuron fires on numeric literals (sequences of digits) 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
     their
    -1.07
     they
    -1.00
     time
    -0.94
     you
    -0.92
     each
    -0.91
    They
    -0.88
     seperti
    -0.86
    story
    -0.85
     such
    -0.84
     vous
    -0.81
    POSITIVE LOGITS
    گیرد
    0.99
    TOMS
    0.98
    München
    0.98
     narrowed
    0.96
    Germania
    0.96
    เป็น
    0.94
    пределение
    0.93
    ENSIONS
    0.92
    班级
    0.91
     vitale
    0.91
    Activations Density 0.015%

    No Known Activations