© 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. 34981
    Prev
    Next
    INDEX
    Explanations

    due diligence

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

    The neuron strongly activates on multi‐digit numerical tokens (i.e. large numeric values).

    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
    IBar
    -0.81
     Manip
    -0.81
    sprecher
    -0.80
     bevel
    -0.78
    designer
    -0.77
     Weibo
    -0.76
    стор
    -0.75
    鳞
    -0.73
    йка
    -0.73
     Crack
    -0.73
    POSITIVE LOGITS
     due
    4.72
     Due
    4.00
    Due
    3.94
    due
    3.72
     DUE
    3.17
     devido
    2.84
     diligence
    2.77
    DUE
    2.75
     debido
    2.73
    由于
    2.19
    Activations Density 0.029%

    No Known Activations