© 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. 39323
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    The neuron fires on Java statement endings—specifically the token sequence “);” marking the close of a method call.

    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
     regalías
    -1.16
    憚
    -1.14
     terceiro
    -1.13
    瞩
    -1.09
     jugando
    -1.08
     nowy
    -1.06
    侂
    -1.06
     Propriété
    -1.03
     destinée
    -1.03
    becomes
    -1.03
    POSITIVE LOGITS
     instinctive
    0.87
    єю
    0.87
     on
    0.85
    情人
    0.82
    地狱
    0.81
     ////
    0.81
     sympathetic
    0.81
    作品の
    0.81
    in
    0.80
     beträgt
    0.80
    Activations Density 0.001%

    No Known Activations