© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63364
    Prev
    Next
    INDEX
    Explanations

    session storage and retrieval

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

    This neuron detects references to client‐ or server‐side storage APIs (e.g. localStorage, session storage, JSON.stringify).

    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
     santé
    -0.82
    эг
    -0.79
     Signs
    -0.79
    Hauteur
    -0.79
    待つ
    -0.78
     turística
    -0.73
     nh
    -0.72
     any
    -0.72
    constitu
    -0.71
     вижу
    -0.71
    POSITIVE LOGITS
    getItem
    1.38
    setItem
    0.95
    Available
    0.92
    薗
    0.92
    Item
    0.88
    GetItem
    0.87
    available
    0.86
    primarily
    0.86
    ppe
    0.85
    ?\\
    0.85
    Activations Density 0.003%

    No Known Activations