© 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. 72473
    Prev
    Next
    INDEX
    Explanations

    file output stream writer

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

    The neuron flags mentions of output‐oriented I/O classes and constructors (e.g. PrintWriter, FileWriter, FileOutputStream, PrintStream, OutputStream).

    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
    P
    -1.41
    N
    -1.30
    C
    -1.26
    H
    -1.11
    B
    -1.09
    at
    -1.06
    w
    -1.06
    U
    -1.05
    L
    -1.05
    u
    -1.04
    POSITIVE LOGITS
    bians
    1.13
    Quercus
    1.09
     Hva
    1.04
    ţiile
    1.04
    argento
    1.02
     anaknya
    1.00
    icians
    1.00
     savannah
    1.00
     perempuan
    0.99
     maladie
    0.97
    Activations Density 0.006%

    No Known Activations