© 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. 22-GEMMASCOPE-RES-131K
    7. 131049
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on integer literal tokens (numeric constants) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    hash map and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    umpulan
    -1.05
    vább
    -1.04
    người
    -1.02
     για
    -0.98
     for
    -0.94
     для
    -0.94
     auténtica
    -0.92
    Dichloroprop
    -0.90
    itee
    -0.89
     pentru
    -0.89
    POSITIVE LOGITS
     correspondance
    1.02
     precau
    0.91
     volu
    0.89
     Presto
    0.88
    imanapun
    0.87
    実験
    0.86
    ينية
    0.86
     lazer
    0.85
     presto
    0.85
     چیز
    0.85
    Activations Density 0.006%

    No Known Activations