© 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. 54102
    Prev
    Next
    INDEX
    Explanations

    patent application references

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

    The neuron detects mentions of other publications or filings (e.g. references to “our accompanying paper,” “copending application,” patent serial numbers, etc.).

    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
     then
    -0.90
    wiście
    -0.88
     então
    -0.88
    满了
    -0.85
     primeira
    -0.81
     defunct
    -0.76
    ليات
    -0.76
    初の
    -0.75
     start
    -0.75
     πρώ
    -0.75
    POSITIVE LOGITS
     separately
    1.62
    separate
    1.47
     separate
    1.47
    Separate
    1.25
     elsewhere
    1.11
     tomorrow
    1.10
     accompanying
    1.08
     today
    1.06
    separ
    1.06
     companion
    1.02
    Activations Density 0.102%

    No Known Activations