© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111657
    Prev
    Next
    INDEX
    Explanations

    stream and writer IO

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

    references to streams and stream-related objects in programming code, particularly output streams like `MemoryStream`, `ostream`, and `System.IO`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on code tokens naming stream or I/O objects and operations (e.g. MemoryStream, sstream, IO, ostream, out).

    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
     our
    -1.63
     between
    -1.48
     vettore
    -1.46
    carian
    -1.43
    ménage
    -1.41
     your
    -1.40
     Ursache
    -1.39
     involving
    -1.38
     conferencias
    -1.35
     veicolo
    -1.30
    POSITIVE LOGITS
     affiche
    1.34
    MacBook
    1.33
     persoalan
    1.32
    ☑️
    1.30
    isateur
    1.29
     Artes
    1.28
     SOLUTIONS
    1.28
    ☎️
    1.27
    titud
    1.27
     ANSWERS
    1.27
    Activations Density 0.024%

    No Known Activations