© 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. 47583
    Prev
    Next
    INDEX
    Explanations

    Pascal interpreters and programming

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

    The neuron strongly activates on the token “Pascal,” i.e. occurrences of the Pascal programming‐language name.

    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
    衚
    -3.13
     แต่
    -2.78
    
    -2.70
    llavero
    -2.66
     abrió
    -2.59
    ± 
    -2.56
    夘
    -2.56
    呿
    -2.55
    盌
    -2.55
    䊐
    -2.52
    POSITIVE LOGITS
    er
    3.47
    ”
    3.13
    In
    3.13
    F
    3.05
    D
    2.55
    ”:
    2.39
    Now
    2.20
    那些
    2.17
    ”;
    2.17
    the
    2.16
    Activations Density 0.002%

    No Known Activations