© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13753
    Prev
    Next
    INDEX
    Explanations

    home page navigation

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

    The neuron activates on site navigation labels and menu/header UI elements (e.g. “Home,” “Main Menu,” “Skip to Main Content”).

    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
     when
    -1.49
    )}$
    -1.23
     because
    -1.17
     When
    -1.16
     that
    -1.16
    >)</
    -1.05
    )}
    
    -1.04
     in
    -1.01
     behalf
    -0.98
    roba
    -0.98
    POSITIVE LOGITS
     page
    1.19
     consommer
    1.09
     affich
    1.08
     PLAINTIFF
    1.05
    基本的に
    1.05
     diyor
    1.05
     ruido
    1.04
    bereiche
    1.01
     objectifs
    0.99
    titial
    0.98
    Activations Density 0.073%

    No Known Activations