© 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. 22-GEMMASCOPE-RES-131K
    7. 98433
    Prev
    Next
    INDEX
    Explanations

    vertical layout orientation

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

    The neuron fires on tokens specifying a vertical layout direction (e.g. “column” or “vertical”).

    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
     故事
    -1.20
     attuale
    -1.13
     to
    -1.13
     wichtiger
    -1.12
     vielfach
    -1.09
     erwäh
    -1.08
     behaupten
    -1.06
     esquecer
    -1.03
     нами
    -1.03
     bestimm
    -1.02
    POSITIVE LOGITS
     efficaces
    1.37
     fó
    1.20
     []:
    1.19
     dekol
    1.16
     reager
    1.16
    ності
    1.16
     recepción
    1.15
     dolores
    1.14
    。
    1.14
     וב
    1.14
    Activations Density 0.001%

    No Known Activations