© 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. 10-GEMMASCOPE-RES-131K
    4. 104948
    Prev
    Next
    INDEX
    Explanations

    programming assertion keyword

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

    the word "assert" in code, particularly in import statements and function calls.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is specialized to detect occurrences of the token “assert,” i.e. assertion calls in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    姈
    -3.02
     was
    -2.77
    ?”
    -2.41
    และ
    -2.41
     découver
    -2.36
    )("
    -2.31
     și
    -2.27
    掼
    -2.25
    Ꭸ
    -2.19
    
    -2.17
    POSITIVE LOGITS
    ?
    3.41
    ).
    3.25
    ),
    3.14
    s
    3.00
    '
    2.94
    -
    2.83
    1
    2.59
    [
    2.50
    \
    2.48
    ers
    2.44
    Activations Density 0.003%

    No Known Activations