© 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. 66159
    Prev
    Next
    INDEX
    Explanations

    license file includes

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

    This neuron detects standalone numeric tokens (strings 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_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
     сум
    -0.75
     Voltaire
    -0.71
    dialement
    -0.69
    詢
    -0.68
    Dew
    -0.66
    俚
    -0.66
    véni
    -0.66
    HART
    -0.66
    buya
    -0.65
    𝐮
    -0.65
    POSITIVE LOGITS
     jeruk
    0.66
    ………………………………
    0.66
     pomocy
    0.65
    ッセージ
    0.64
    Returned
    0.63
    лые
    0.62
     biographical
    0.62
     photographers
    0.62
    novo
    0.61
    失敗
    0.61
    Activations Density 0.065%

    No Known Activations