© 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. 10-GEMMASCOPE-RES-131K
    7. 70849
    Prev
    Next
    INDEX
    Explanations

    head words forming compounds

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

    This neuron responds to numeric expressions (whole numbers and decimal values) 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_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
    
    -2.09
    歺
    -2.03
    蕖
    -1.93
    秶
    -1.92
    乁
    -1.92
     wszystkich
    -1.90
    weren
    -1.84
    艄
    -1.84
     cuja
    -1.82
    
    -1.82
    POSITIVE LOGITS
     by
    2.25
     will
    2.16
     as
    2.13
     these
    2.09
     if
    2.08
    -
    2.05
     has
    1.92
     or
    1.92
     having
    1.89
     should
    1.85
    Activations Density 0.775%

    No Known Activations