© 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. 84088
    Prev
    Next
    INDEX
    Explanations

    saving data before closing

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

    The neuron fires on imperative instruction phrases in code comments (e.g. “Override to perform setup…,” “Clean up any resources…,” “stop music,” etc.).

    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
     harta
    -1.09
     bliver
    -1.05
    достатки
    -1.05
     alip
    -1.01
     konsult
    -0.98
    ㎖
    -0.97
     tempel
    -0.96
     öv
    -0.96
     gitar
    -0.95
     each
    -0.94
    POSITIVE LOGITS
    Produkte
    1.31
     BytesLike
    1.13
    Vedi
    1.12
     σελ
    1.09
    ૯
    1.06
     etc
    1.02
     אך
    1.01
    ffiti
    1.01
    achery
    1.01
    ^{-
    1.00
    Activations Density 0.004%

    No Known Activations