© 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. 65296
    Prev
    Next
    INDEX
    Explanations

    numbers before units

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

    The neuron activates on numeric tokens—both digit strings and number words—identifying occurrences of quantities or counts 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
     thousands
    -0.89
    hundreds
    -0.88
    Hundreds
    -0.86
     dozen
    -0.85
     hundreds
    -0.83
    ecution
    -0.82
     eing
    -0.81
    が終わ
    -0.81
    acamole
    -0.80
    Thousands
    -0.79
    POSITIVE LOGITS
     meste
    0.89
     maksimal
    0.89
    ностей
    0.84
     pesar
    0.82
    ﹒
    0.82
     deutlich
    0.81
    ﻮ
    0.81
    ⏳
    0.81
    rierten
    0.81
     recensement
    0.81
    Activations Density 0.092%

    No Known Activations