© 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. 10-GEMMASCOPE-RES-131K
    7. 103992
    Prev
    Next
    INDEX
    Explanations

    array declaration

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

    the word "array" in PHP code.

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

    The neuron activates on PHP “array(…)” constructs—that is, it spots occurrences of the keyword “array” when defining arrays.

    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
     also
    -2.95
     have
    -2.41
     and
    -2.14
        
    -2.02
    调整
    -1.96
     know
    -1.91
    ’,
    -1.89
     should
    -1.88
    AL
    -1.86
     from
    -1.83
    POSITIVE LOGITS
    酲
    2.34
     PRIZE
    2.33
     FESTIVAL
    2.27
     CHAMPION
    2.23
    ♥♥
    2.17
     tarifs
    2.16
     Meilleur
    2.14
     TORONTO
    2.14
    鈁
    2.11
     SPANISH
    2.08
    Activations Density 0.007%

    No Known Activations