© 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. 9733
    Prev
    Next
    INDEX
    Explanations

    programming data types

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

    This neuron fires on the parentheses and commas of function or constructor parameter lists, effectively spotting method signatures.

    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
    つい
    -0.88
     Gestaltung
    -0.88
     third
    -0.86
     Bedürfnisse
    -0.84
     quatrième
    -0.83
    還有
    -0.82
     Entscheidungen
    -0.82
     pédagog
    -0.81
     praktischen
    -0.81
     Forderungen
    -0.81
    POSITIVE LOGITS
    り物
    0.95
    ⍵
    0.86
     thì
    0.86
     Horizonte
    0.85
     angusti
    0.85
     adulti
    0.84
     penal
    0.84
    
    0.84
     reptiles
    0.83
     captivity
    0.83
    Activations Density 0.004%

    No Known Activations