© 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. 90608
    Prev
    Next
    INDEX
    Explanations

    variable assignment

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

    The neuron detects code identifiers, especially common variable and type names in programming snippets.

    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
     easily
    -0.94
     both
    -0.93
     will
    -0.93
    Exeunt
    -0.92
     others
    -0.92
     nothing
    -0.92
    tanda
    -0.89
     each
    -0.89
     costruire
    -0.88
     Verständnis
    -0.88
    POSITIVE LOGITS
    »).
    1.07
    ).</
    0.99
     neste
    0.94
    »),
    0.92
     sorgen
    0.92
    »)
    0.88
    )».
    0.87
     engl
    0.87
     '*')
    0.85
    ]))
    
    0.85
    Activations Density 0.027%

    No Known Activations