© 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. 10-GEMMASCOPE-RES-131K
    7. 71651
    Prev
    Next
    INDEX
    Explanations

    IndexedDB API concepts

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

    The neuron fires on references to the IndexedDB API (e.g. “IndexedDB,” “DB,” “ObjectStore,” “Path,” 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_10/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
     was
    -1.51
    ?”
    -1.34
     rasgos
    -1.28
    "=>
    -1.26
     aceea
    -1.24
    睃
    -1.21
    同样的
    -1.20
     Kowal
    -1.20
     específica
    -1.20
    tió
    -1.20
    POSITIVE LOGITS
     Wszyst
    1.38
    Tutto
    1.38
    tahan
    1.35
     כאן
    1.30
    rdi
    1.27
     more
    1.27
     profoundly
    1.27
    球队
    1.24
     but
    1.21
    的人都
    1.21
    Activations Density 0.025%

    No Known Activations