© 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. 34-GEMMASCOPE-RES-131K
    7. 2134
    Prev
    Next
    INDEX
    Explanations

    date and numbers

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

    The neuron activates on code‐like function or method call syntax, especially the parentheses (and commas) surrounding arguments in programming calls.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     benefits
    -0.68
     randomly
    -0.67
    ⇥
    -0.65
    bolistas
    -0.65
     positiv
    -0.64
     cres
    -0.64
     vibes
    -0.63
     הבי
    -0.62
     silently
    -0.62
     الموا
    -0.62
    POSITIVE LOGITS
     bestätigen
    0.77
    strument
    0.74
     aika
    0.72
     importância
    0.72
    ارة
    0.72
     waive
    0.72
     ngoại
    0.71
    ėj
    0.71
     rozpoczę
    0.71
    ễn
    0.70
    Activations Density 0.079%

    No Known Activations