© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90384
    Prev
    Next
    INDEX
    Explanations

    serialize, stringify, inspect

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

    The neuron activates on method names used to serialize or convert data into string form (e.g. stringify, dumps, toString, toSource, toDateString).

    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
    圌
    -1.46
    埽
    -1.43
    }=\
    -1.42
    }
    -1.39
     raiſ
    -1.38
    跺
    -1.37
    のための
    -1.36
     také
    -1.34
    艄
    -1.34
    嚎
    -1.33
    POSITIVE LOGITS
     of
    1.92
    珝
    1.68
    Surprisingly
    1.66
     explí
    1.63
     Anschließend
    1.59
    Recently
    1.55
     lokalen
    1.55
    Since
    1.52
    Have
    1.52
    Just
    1.51
    Activations Density 0.017%

    No Known Activations