© 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. 130602
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting standalone numeric literals (numbers) in source code.

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

    programming code constructs

    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
    sequent
    -0.85
    行
    -0.82
    ネマ
    -0.82
    illam
    -0.81
     παρου
    -0.80
     Gebruik
    -0.79
    ября
    -0.78
    BEFORE
    -0.77
     perang
    -0.76
    LJ
    -0.76
    POSITIVE LOGITS
     accordance
    0.87
     virš
    0.85
    Según
    0.84
     zgodnie
    0.82
    ないです
    0.78
     override
    0.77
     negligible
    0.77
     will
    0.76
     также
    0.75
    GNUC
    0.75
    Activations Density 0.026%

    No Known Activations