© 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. 102459
    Prev
    Next
    INDEX
    Explanations

    storing and retrieving key-value data

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

    The neuron activates on mentions of storage or persistence API calls (e.g. AsyncStorage, Session::put, localStorage, cookies, SharedPreferences, registry PATH).

    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
    neous
    -0.88
    водится
    -0.84
    CSV
    -0.82
    ulfate
    -0.77
    HALT
    -0.76
    ടു
    -0.75
     масса
    -0.75
    PointerException
    -0.75
    atisme
    -0.74
     także
    -0.73
    POSITIVE LOGITS
     keys
    1.24
     storing
    1.00
     setObject
    0.99
    containsKey
    0.96
    keySet
    0.94
    keys
    0.94
     key
    0.92
    値
    0.91
    KEYS
    0.91
    getItem
    0.91
    Activations Density 0.015%

    No Known Activations