© 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. 13122
    Prev
    Next
    INDEX
    Explanations

    code and programming syntax

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

    The neuron fires on numeric literal tokens (i.e. 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
    Ώ
    -0.84
     escase
    -0.84
    直到
    -0.83
     podéis
    -0.76
    橿
    -0.75
     posts
    -0.73
    ículas
    -0.73
    artement
    -0.71
    ribusi
    -0.71
    꼭
    -0.70
    POSITIVE LOGITS
     Eugen
    0.92
    şağı
    0.75
    発生
    0.75
    寶
    0.74
     Crawford
    0.74
     sayap
    0.74
    dima
    0.72
     homogenous
    0.71
    ânea
    0.71
     febr
    0.70
    Activations Density 0.006%

    No Known Activations