© 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. 34910
    Prev
    Next
    INDEX
    Explanations

    special characters and code snippets

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

    The neuron flags document-structure tokens—section headings, labels, and other formatting/metadata markers that organize the 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
     berbagai
    -0.94
    ื้อ
    -0.81
    Profess
    -0.78
    郝
    -0.75
    Statue
    -0.75
    alló
    -0.75
    эффици
    -0.75
    ラインナップ
    -0.74
    Lla
    -0.74
     воло
    -0.73
    POSITIVE LOGITS
    setViewportView
    1.13
    xty
    0.87
    TargetException
    0.85
    这次
    0.81
    borderFill
    0.80
     intended
    0.79
     espectáculo
    0.79
     város
    0.77
    äldrar
    0.76
    Kir
    0.76
    Activations Density 0.103%

    No Known Activations