© 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. 34-GEMMASCOPE-RES-131K
    7. 59258
    Prev
    Next
    INDEX
    Explanations

    memory and thinking

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

    The neuron strongly activates on words and phrases referring to storing or retaining memory or information (e.g. “store,” “memory,” “RAM,” “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_34/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
     memories
    -1.28
    MEMORY
    -1.17
     memory
    -1.13
    Memories
    -0.98
    memory
    -0.97
     Memories
    -0.92
     macrophages
    -0.91
     RAM
    -0.90
     didReceive
    -0.88
    InMemory
    -0.88
    POSITIVE LOGITS
    Ǧ
    0.71
     gonad
    0.66
     biscuits
    0.66
     Kali
    0.64
    Executing
    0.63
    inizio
    0.63
    不觉
    0.63
     Vander
    0.63
     Novak
    0.62
     aspar
    0.60
    Activations Density 0.039%

    No Known Activations