© 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. 70309
    Prev
    Next
    INDEX
    Explanations

    actions leading to outcomes

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

    The neuron activates on numeric tokens—especially integer or decimal numbers—wherever they appear 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
     by
    -2.27
     on
    -1.73
     has
    -1.70
        
    -1.59
     at
    -1.56
     "
    -1.45
     also
    -1.42
     speziellen
    -1.42
     '
    -1.41
    i
    -1.38
    POSITIVE LOGITS
    ATION
    1.43
    البته
    1.38
    Gosh
    1.38
    эф
    1.34
     huid
    1.31
     Suomessa
    1.31
     巾
    1.30
    
    1.30
     desej
    1.29
    zelve
    1.29
    Activations Density 0.064%

    No Known Activations