© 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. 34-GEMMASCOPE-RES-131K
    7. 86901
    Prev
    Next
    INDEX
    Explanations

    shell commands

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

    The neuron fires on programming‐style tokens and syntax (code fragments) embedded in the text.

    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
     mkdir
    -0.82
     kurikulum
    -0.81
     ярма
    -0.74
    BOYS
    -0.71
    urez
    -0.70
    пресс
    -0.70
    LAX
    -0.70
     Jardim
    -0.68
    ائية
    -0.67
     Août
    -0.66
    POSITIVE LOGITS
     cat
    3.28
    cat
    3.09
    Cat
    2.45
     Cat
    2.41
     CAT
    1.90
     cats
    1.84
    CAT
    1.73
    貓
    1.63
    猫
    1.57
     tail
    1.45
    Activations Density 0.128%

    No Known Activations