© 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. 68997
    Prev
    Next
    INDEX
    Explanations

    two or duo

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

    The neuron fires on numeric tokens—especially numbers, fractions, and other digit‐containing expressions.

    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
     all
    -1.22
     todas
    -1.01
     varios
    -0.98
     various
    -0.98
    various
    -0.96
     всех
    -0.93
     सभी
    -0.93
    ?,?,
    -0.92
     wszystkie
    -0.92
    anto
    -0.92
    POSITIVE LOGITS
     two
    1.62
     duo
    1.50
    这两个
    1.30
     berdua
    1.29
     beiden
    1.28
     båda
    1.26
    两
    1.24
     Beide
    1.21
    兩
    1.20
     двух
    1.16
    Activations Density 0.233%

    No Known Activations