© 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. 34-GEMMASCOPE-RES-131K
    7. 73606
    Prev
    Next
    INDEX
    Explanations

    numbers, questions, code

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

    The neuron strongly activates on tokens representing numeric values (digits, numbers, or numeric 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_34/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
     Перейти
    -0.88
     memang
    -0.88
     kỷ
    -0.87
     kategori
    -0.86
     плюс
    -0.85
    Ừ
    -0.83
     espaces
    -0.82
     kategor
    -0.82
     ـ
    -0.82
     Políticas
    -0.81
    POSITIVE LOGITS
     изобра
    1.05
     churchyard
    1.00
    orestation
    0.92
    !
    0.92
     tersebut
    0.89
     observing
    0.89
     xPos
    0.88
    יקר
    0.85
    observable
    0.85
     paying
    0.85
    Activations Density 0.001%

    No Known Activations