© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118011
    Prev
    Next
    INDEX
    Explanations

    framework components and methods

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

    The neuron fires on occurrences of PHP’s scope‐resolution operator (“::”), i.e. static/class constant or static method references.

    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
     avete
    -0.98
    RICULUM
    -0.97
     sogni
    -0.94
    getColumnIndex
    -0.90
    ENTINA
    -0.90
    但
    -0.89
    ttää
    -0.88
    йти
    -0.88
     vacanza
    -0.87
     tartalomajánló
    -0.87
    POSITIVE LOGITS
     getInstance
    1.15
     nao
    1.11
    _:
    1.05
    lý
    1.04
    媜
    1.01
     enquanto
    1.00
     ní
    0.96
    +```
    0.96
      
    0.96
    的其他
    0.96
    Activations Density 0.004%

    No Known Activations