© 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. 129615
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numeric literals (numbers) in code.

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

    programming output functions

    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
     jugado
    -0.98
     langer
    -0.98
    ٬
    -0.97
    peut
    -0.95
    nate
    -0.93
    eturn
    -0.93
     maximale
    -0.91
     ince
    -0.89
    Răspunde
    -0.86
     FÜR
    -0.86
    POSITIVE LOGITS
     these
    0.96
    These
    0.91
     chcia
    0.91
     gets
    0.90
     list
    0.90
     gives
    0.88
     came
    0.87
     ними
    0.85
     öss
    0.85
    There
    0.84
    Activations Density 0.001%

    No Known Activations