© 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. 67107
    Prev
    Next
    INDEX
    Explanations

    program arguments and variable names

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

    This neuron primarily detects numeric literals (integer constants) 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
     for
    -1.36
     this
    -1.09
     only
    -1.07
     concern
    -1.05
     entire
    -1.02
     here
    -1.01
     being
    -0.97
     him
    -0.96
     not
    -0.96
     that
    -0.94
    POSITIVE LOGITS
    Forza
    1.05
    Теперь
    1.04
    César
    0.98
    véni
    0.96
    Сообщение
    0.96
    Хотя
    0.96
     squadrons
    0.96
     հղումներ
    0.96
    Кроме
    0.95
     edile
    0.95
    Activations Density 0.001%

    No Known Activations