© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16017
    Prev
    Next
    INDEX
    Explanations

    Physio logic, questions, Fidel, Sun filled

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

    The neuron fires on numeric literals and standalone digits (e.g. “0”, “1”, … “4”) in code or 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
     牛奶
    -1.16
    terrasse
    -1.03
     mód
    -1.02
     arquitecto
    -1.01
     symbole
    -1.01
    claro
    -0.99
     préparation
    -0.98
     símbolos
    -0.98
    ğini
    -0.98
     cofre
    -0.97
    POSITIVE LOGITS
     gepubliceerd
    0.96
     fornic
    0.91
    用戶
    0.90
     belligerent
    0.90
     continuing
    0.88
    用到
    0.87
     gepub
    0.87
    働く
    0.86
    ります
    0.85
     Pingback
    0.84
    Activations Density 0.003%

    No Known Activations