© 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. 240
    Prev
    Next
    INDEX
    Explanations

    code constructs and programming terms

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

    The neuron is tuned to detect numeric literals (numbers) 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
     весело
    -0.90
    kgs
    -0.88
     sindaco
    -0.88
     เด็ก
    -0.85
     вверх
    -0.85
    另一个
    -0.85
     CORPORATION
    -0.85
     gutt
    -0.85
    örgy
    -0.84
     būt
    -0.83
    POSITIVE LOGITS
    Tür
    1.02
    FDRE
    1.00
     ajuda
    0.98
    ஊ
    0.93
    だったら
    0.92
    rvore
    0.91
    Веду
    0.91
    ekten
    0.91
     рю
    0.91
    odat
    0.90
    Activations Density 0.030%

    No Known Activations