© 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. 22-GEMMASCOPE-RES-131K
    7. 65105
    Prev
    Next
    INDEX
    Explanations

    Java file I/O and data handling

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

    The neuron detects mentions of Java I/O stream classes (like BufferedReader, PrintWriter, DataInputStream, etc.) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     如果
    -2.00
     \
    -1.96
    at
    -1.82
    其他
    -1.78
    es
    -1.77
     we
    -1.77
     มี
    -1.71
     Its
    -1.66
    并不是
    -1.63
     —
    -1.59
    POSITIVE LOGITS
     menthe
    1.86
    鍆
    1.78
    鶿
    1.71
     magazin
    1.64
     ponts
    1.63
     actie
    1.63
     maroc
    1.63
     rossi
    1.62
     projets
    1.61
    龊
    1.61
    Activations Density 0.001%

    No Known Activations