© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107830
    Prev
    Next
    INDEX
    Explanations

    legal and formal phrases

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

    The neuron primarily detects numeric tokens and digit sequences (e.g. dates, case numbers, amounts).

    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
     for
    -1.13
     while
    -1.12
     additional
    -1.05
     from
    -0.98
     it
    -0.96
     Typically
    -0.95
     coupled
    -0.90
    لفة
    -0.90
     focusing
    -0.90
     during
    -0.89
    POSITIVE LOGITS
     astonishing
    1.05
     delightfully
    1.00
    ècle
    0.98
     предъ
    0.97
     .........
    0.96
     .......
    0.95
     ludicrous
    0.94
     astounding
    0.94
     exhilarating
    0.94
     ornate
    0.93
    Activations Density 0.002%

    No Known Activations