© 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. 38559
    Prev
    Next
    INDEX
    Explanations

    foreign language labels and descriptors

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

    The neuron strongly activates on brief section headings or metadata labels (like “Presse portal,” “Resumen,” “Mehr,” “vor … Stunden,” Japanese photo captions, etc.) that typically introduce or label content in various languages.

    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
     two
    -1.48
     should
    -1.42
     both
    -1.40
     before
    -1.35
     several
    -1.33
     develop
    -1.30
     will
    -1.29
     after
    -1.27
     could
    -1.26
    とある
    -1.21
    POSITIVE LOGITS
     heilige
    1.27
    EVERY
    1.24
     verborgen
    1.23
    鱂
    1.22
    approximately
    1.21
    similar
    1.16
     schuldig
    1.16
    
    1.16
     geze
    1.16
    ąpi
    1.16
    Activations Density 0.017%

    No Known Activations