© 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. 11968
    Prev
    Next
    INDEX
    Explanations

    cache and caching

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

    The neuron detects references to caching functionality—e.g. tokens like “cache,” “cached,” “lru_cache,” “memoize,” 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_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
    atars
    -0.80
    чені
    -0.76
     rétro
    -0.76
    oreille
    -0.73
    ophyta
    -0.73
    cucumber
    -0.73
     Reid
    -0.72
     voort
    -0.71
     Normdatei
    -0.71
     अस
    -0.70
    POSITIVE LOGITS
     cache
    5.03
    cache
    4.34
     caching
    4.16
    Cache
    4.16
     cached
    4.06
    缓存
    3.94
     Cache
    3.91
    CACHE
    3.86
     caches
    3.70
    getCache
    3.45
    Activations Density 0.090%

    No Known Activations