© 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. 86934
    Prev
    Next
    INDEX
    Explanations

    in-memory systems

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

    The neuron responds strongly to numeric literals and their associated punctuation or assignment operators (e.g. numbers, arrows, colons, equals signs) in code or configuration contexts.

    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
     ácidos
    -0.71
    ji
    -0.71
     boyunca
    -0.70
    patra
    -0.69
    stein
    -0.69
    ператор
    -0.68
    gls
    -0.67
    ポーター
    -0.66
     sóng
    -0.66
     mencegah
    -0.65
    POSITIVE LOGITS
     memory
    3.23
    内存
    3.00
    memory
    2.80
    InMemory
    2.67
     Memory
    2.47
    MEMORY
    2.41
    Memory
    2.36
     MEMORY
    2.27
     memories
    2.20
     RAM
    1.99
    Activations Density 0.088%

    No Known Activations