© 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. 73587
    Prev
    Next
    INDEX
    Explanations

    date and number

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

    The neuron strongly activates on numeric tokens (especially multi‐digit numbers).

    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
    正在
    -0.93
    НОЙ
    -0.76
    asmuch
    -0.72
    puente
    -0.71
    ulling
    -0.71
    浪费
    -0.70
    交给
    -0.69
    FIVE
    -0.69
     khuy
    -0.69
     mascarilla
    -0.68
    POSITIVE LOGITS
    forma
    0.70
     Edizioni
    0.64
    込め
    0.64
    恭喜
    0.63
     Rosas
    0.63
     Basil
    0.62
     नी
    0.62
     Brother
    0.62
     FR
    0.61
     activities
    0.61
    Activations Density 0.050%

    No Known Activations