© 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. 22-GEMMASCOPE-RES-131K
    7. 34939
    Prev
    Next
    INDEX
    Explanations

    professional processes and qualifications

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

    The neuron fires on content‐bearing terms—especially nouns, gerunds, and other topic-specific keywords that denote services, actions, or key concepts in a 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_22/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
    展开
    -0.92
     --
    -0.86
    breviations
    -0.84
     عبدالله
    -0.83
    chemise
    -0.80
     aking
    -0.80
     left
    -0.79
    老师
    -0.78
     backend
    -0.78
     deseas
    -0.77
    POSITIVE LOGITS
     appelez
    1.16
    ئي
    1.08
     WERE
    1.05
     игрушка
    1.05
    yao
    1.05
     históricas
    1.02
    ubei
    1.02
     informó
    1.02
     zwarte
    1.01
    িয়া
    1.01
    Activations Density 0.106%

    No Known Activations