© 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. 22-GEMMASCOPE-RES-131K
    7. 35786
    Prev
    Next
    INDEX
    Explanations

    index numbering

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

    This neuron detects numeric literals (numbers) 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_22/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
     aš
    -0.89
    niet
    -0.81
     durabilidad
    -0.81
     nových
    -0.77
     AppColors
    -0.77
     velikost
    -0.77
    hý
    -0.75
     leña
    -0.75
    も行
    -0.75
    iarkan
    -0.74
    POSITIVE LOGITS
     pandemi
    1.05
     antik
    0.90
    whether
    0.89
     aktivi
    0.85
     rata
    0.85
     itali
    0.85
    irinha
    0.84
    aturan
    0.83
    INAS
    0.83
     vekt
    0.82
    Activations Density 0.010%

    No Known Activations