© 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. 7134
    Prev
    Next
    INDEX
    Explanations

    cache and freshness

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

    The neuron fires on mentions of HTTP status codes (especially “200”) in text.

    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
    texttt
    -0.83
    essions
    -0.80
     světě
    -0.75
     charcoal
    -0.75
     fluorine
    -0.75
     Krypton
    -0.75
     Charcoal
    -0.73
     prototyping
    -0.72
     barnen
    -0.71
     precaution
    -0.71
    POSITIVE LOGITS
     cache
    1.32
    cache
    1.09
    Cache
    1.05
     freshness
    0.97
    缓存
    0.94
    キャ
    0.93
     Cache
    0.85
     CACHE
    0.85
    fresh
    0.84
     diferencial
    0.84
    Activations Density 0.026%

    No Known Activations