© 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. 23656
    Prev
    Next
    INDEX
    Explanations

    equal monthly payments

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

    The neuron is tuned to pick out numeric tokens (digits and multi-digit number sequences) 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
    Fed
    -0.91
     دقیقه
    -0.76
     Fed
    -0.73
    ɧ
    -0.72
    igel
    -0.69
    länder
    -0.69
     utilitarian
    -0.69
     cuentas
    -0.68
     geography
    -0.68
    ménage
    -0.68
    POSITIVE LOGITS
     installments
    2.28
     installment
    2.06
     instalments
    2.05
     instalment
    1.80
    Install
    1.73
     Install
    1.70
    install
    1.65
     Instal
    1.31
     instal
    1.27
    Instal
    1.22
    Activations Density 0.020%

    No Known Activations