© 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. 73667
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and urls

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

    The neuron fires strongly on the “href=” parts of HTML anchors, i.e. the URLs inside link tags.

    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
     fiind
    -1.05
    Durata
    -1.01
     Unterricht
    -1.00
     Unterrichts
    -0.98
     zmian
    -0.96
     kebutuhan
    -0.94
     Auswahl
    -0.94
    subaru
    -0.93
     foro
    -0.91
     августа
    -0.90
    POSITIVE LOGITS
    şil
    1.09
     跳转至
    1.05
    ##############
    0.96
     artikke
    0.94
    íticos
    0.94
     ***/
    0.93
    íram
    0.90
    このように
    0.89
    XtraEditors
    0.89
    正好
    0.89
    Activations Density 0.003%

    No Known Activations