© 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. 34-GEMMASCOPE-RES-131K
    7. 8404
    Prev
    Next
    INDEX
    Explanations

    index numbers

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

    The neuron specializes in spotting numeric tokens—integer literals, counts, indices, sizes, and other number-related identifiers—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_34/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
    ändige
    -0.82
     Perse
    -0.80
     pene
    -0.78
     INITI
    -0.74
    ℰ
    -0.74
     chariot
    -0.72
     kablo
    -0.72
     pere
    -0.72
     umbre
    -0.71
     Horus
    -0.71
    POSITIVE LOGITS
     integers
    1.08
     usize
    1.04
    selectedIndex
    0.93
     getIndex
    0.85
    usize
    0.83
    idxs
    0.83
     indexes
    0.81
     integer
    0.77
    索引
    0.77
     étrangère
    0.77
    Activations Density 0.028%

    No Known Activations