© 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. 10-GEMMASCOPE-RES-131K
    7. 21933
    Prev
    Next
    INDEX
    Explanations

    tables and diagrams

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

    This neuron activates on mentions or uses of structured visual representations—specifically tables and diagrams.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     –
    -1.40
    unno
    -1.28
     ‘
    -1.24
     passagers
    -1.20
    ִּ
    -1.20
     celle
    -1.19
    jamientos
    -1.19
    хий
    -1.17
     séjours
    -1.17
    mogen
    -1.17
    POSITIVE LOGITS
     for
    1.55
    ῖς
    1.36
     myself
    1.26
     they
    1.26
    ڡ
    1.24
     Даже
    1.23
     proposte
    1.22
     confiable
    1.20
     one
    1.19
    我會
    1.16
    Activations Density 0.071%

    No Known Activations