© 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. 60764
    Prev
    Next
    INDEX
    Explanations

    cache and eviction

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     methanol
    -0.78
    neat
    -0.75
    nessione
    -0.74
    uther
    -0.73
    мир
    -0.73
    attendre
    -0.72
    ⊃
    -0.71
    ᴉ
    -0.71
    plasma
    -0.71
    wax
    -0.71
    POSITIVE LOGITS
    淘汰
    1.09
     cache
    1.03
    cache
    1.01
    LinkedHashMap
    0.90
    Cache
    0.89
     recent
    0.85
     recently
    0.85
    最近
    0.82
     eviction
    0.82
     Cache
    0.81
    Activations Density 0.007%

    No Known Activations