© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 38790
    Prev
    Next
    INDEX
    Explanations

    css classes for columns

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

    This neuron detects numeric tokens (numbers, including integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    だったが
    -1.41
    ).
    -1.33
    几分
    -1.29
    -
    -1.29
     the
    -1.29
    SaveChangesAsync
    -1.27
    
    -1.27
     a
    -1.27
    оны
    -1.27
     quedaron
    -1.27
    POSITIVE LOGITS
     Songtext
    1.49
    няет
    1.45
    šenie
    1.43
     icona
    1.41
     الثانية
    1.41
    既に
    1.40
    ERICA
    1.36
    違う
    1.36
     التالية
    1.35
     Those
    1.34
    Activations Density 0.003%

    No Known Activations