© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117367
    Prev
    Next
    INDEX
    Explanations

    patent numbers, questions, technical/scientific terms

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

    The neuron is a detector for highly technical, industrial‐materials vocabulary (e.g. specialized nouns like “fiber,” “blankets,” “modules,” etc.) often found in engineering or patent descriptions.

    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
    头的
    -0.74
     hailed
    -0.70
    speakers
    -0.67
    穎
    -0.66
     speaker
    -0.66
     estimated
    -0.65
     تمت
    -0.65
     exhibit
    -0.64
    企画
    -0.64
     Einrichtung
    -0.64
    POSITIVE LOGITS
    faced
    0.91
     Kna
    0.88
     boards
    0.87
    Fac
    0.83
    Kna
    0.81
     faced
    0.78
    Facade
    0.78
     Faced
    0.78
     façade
    0.77
    azine
    0.75
    Activations Density 0.013%

    No Known Activations