© 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. 33143
    Prev
    Next
    INDEX
    Explanations

    code delimiters and operators

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

    The neuron fires specifically on numeric constants (digits and number literals) 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
     inggris
    -0.81
     dintre
    -0.81
    Pickle
    -0.77
     Mosquito
    -0.77
    sertation
    -0.77
    📫
    -0.74
    듈
    -0.74
     dumplings
    -0.73
     rooftop
    -0.73
     tsu
    -0.73
    POSITIVE LOGITS
     eliminar
    0.90
    any
    0.87
    BeforeClass
    0.85
    ことができる
    0.85
    encounter
    0.85
    Any
    0.82
    áver
    0.80
    correspond
    0.80
     Any
    0.79
     any
    0.79
    Activations Density 0.031%

    No Known Activations