© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99596
    Prev
    Next
    INDEX
    Explanations

    dry cleaning and laundry

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

    The neuron selectively fires on numeric tokens or digit sequences (i.e. numbers and quantities).

    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
     merchandising
    -0.80
    bud
    -0.78
    дравствуйте
    -0.78
     amateurs
    -0.77
    Carrière
    -0.76
    phrag
    -0.75
    Ȼ
    -0.74
    窜
    -0.74
     kasama
    -0.73
     repayment
    -0.72
    POSITIVE LOGITS
     dry
    2.80
     Dry
    2.41
    Dry
    2.16
    dry
    2.13
     DRY
    1.55
    DRY
    1.55
     cleaning
    1.46
     cleaners
    1.29
    クリー
    1.26
    cleaning
    1.24
    Activations Density 0.011%

    No Known Activations