© 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. 80730
    Prev
    Next
    INDEX
    Explanations

    asynchronous programming utilities or parallel operations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    eeqa
    -0.83
    వ
    -0.82
    fag
    -0.81
     MainAxisSize
    -0.79
    電車
    -0.69
    ograms
    -0.69
    ParseException
    -0.68
     Mend
    -0.66
    monial
    -0.66
    typeorm
    -0.65
    POSITIVE LOGITS
     each
    1.03
    each
    0.95
     iterator
    0.95
     parallel
    0.90
     next
    0.89
     waterfall
    0.85
    EACH
    0.84
    parallel
    0.82
    Parallel
    0.82
     paralelo
    0.79
    Activations Density 0.029%

    No Known Activations