© 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. 69066
    Prev
    Next
    INDEX
    Explanations

    numbers and signs

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

    The neuron flags numeric tokens (whole numbers and multi‐digit numerals) when they appear as terms in sequence‐oriented math questions.

    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
     plafon
    -1.21
    ,:,
    -1.16
    หรือ
    -1.12
     permiten
    -1.01
    oare
    -1.00
    雹
    -1.00
     cebola
    -0.99
     milho
    -0.99
    ogni
    -0.98
     میلیارد
    -0.98
    POSITIVE LOGITS
     Только
    1.47
    G
    1.07
    N
    1.06
    R
    1.04
     Конечно
    1.03
     Многие
    1.00
     only
    1.00
    Y
    0.99
    Only
    0.98
    er
    0.98
    Activations Density 0.007%

    No Known Activations