© 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. 67904
    Prev
    Next
    INDEX
    Explanations

    copyright and license statements

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

    The neuron detects doc-block metadata keywords—especially copyright, license (and related @-annotations) in code comments.

    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
     then
    -1.04
     while
    -1.03
     posteriormente
    -1.00
     fijne
    -0.97
     znalaz
    -0.96
     つの
    -0.93
     هایی
    -0.93
     rồi
    -0.93
     często
    -0.92
     danach
    -0.92
    POSITIVE LOGITS
    küche
    1.11
    siehe
    1.10
    ẾT
    1.02
     vider
    1.02
     Siehe
    1.01
     porcentual
    1.01
    種の
    0.96
     Daß
    0.96
    だか
    0.96
    ()}}
    0.95
    Activations Density 0.020%

    No Known Activations