© 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. 93006
    Prev
    Next
    INDEX
    Explanations

    recording or storing information

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

    The neuron fires on words that denote recording, storing, or otherwise noting information.

    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
    쩌
    -0.97
     amazon
    -0.93
     einem
    -0.92
    ဍ
    -0.91
     post
    -0.89
    rijving
    -0.88
     adhesive
    -0.88
     einer
    -0.88
     ใน
    -0.88
    ்த
    -0.86
    POSITIVE LOGITS
     everything
    1.37
     what
    1.13
     незакон
    1.00
    そして
    0.99
    izzati
    0.96
     their
    0.95
     semuanya
    0.92
     VILLA
    0.92
    kový
    0.92
     then
    0.91
    Activations Density 0.052%

    No Known Activations