© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49816
    Prev
    Next
    INDEX
    Explanations

    dual energy X-ray

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

    The neuron detects occurrences of the word “dual” (including as a prefix in technical terms like dual-energy or dual-source).

    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
     cathode
    -0.71
    RTS
    -0.69
     thoughtfully
    -0.68
    Identyfik
    -0.66
     创建
    -0.65
     Finding
    -0.65
     Kuri
    -0.64
    рено
    -0.64
     memory
    -0.63
     tài
    -0.63
    POSITIVE LOGITS
     McMahon
    0.75
    nodata
    0.73
     重
    0.71
    琴
    0.71
    widetext
    0.71
     thanh
    0.69
    વ
    0.68
     onclick
    0.68
     noth
    0.68
    itek
    0.68
    Activations Density 0.062%

    No Known Activations