© 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. 22-GEMMASCOPE-RES-131K
    7. 66237
    Prev
    Next
    INDEX
    Explanations

    logical operators and Nigerian

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

    The neuron fires on numeric literals (digits) in code.

    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
     Genève
    -1.17
     Juillet
    -1.06
     Chapitre
    -1.04
     Produtos
    -1.03
    borderSide
    -1.02
    multer
    -1.01
    和
    -1.01
     mxArray
    -1.01
     commentaires
    -1.01
     BIBLIOGRAPHY
    -1.01
    POSITIVE LOGITS
    sneak
    1.09
    僻
    1.02
    Puss
    1.02
    するの
    1.02
     numerosas
    0.98
    This
    0.97
    咄
    0.97
     sogar
    0.96
     it
    0.95
    striping
    0.95
    Activations Density 0.002%

    No Known Activations