© 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. 110600
    Prev
    Next
    INDEX
    Explanations

    code imports

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

    import or use statements in programming code.

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

    The neuron activates strongly on programming-language import or use statements (i.e. lines bringing in external modules/packages).

    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
     mily
    -1.77
     اخبار
    -1.65
     kredi
    -1.63
     katk
    -1.62
     Bagi
    -1.59
     médicaments
    -1.55
     Ça
    -1.54
     willen
    -1.51
     imponer
    -1.51
     thier
    -1.50
    POSITIVE LOGITS
     now
    2.16
     will
    2.13
     other
    2.02
    }{
    1.89
     more
    1.89
     still
    1.86
    </em>
    1.81
    This
    1.80
    %;
    
    1.77
    </
    1.73
    Activations Density 0.053%

    No Known Activations