© 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. 34-GEMMASCOPE-RES-131K
    7. 30356
    Prev
    Next
    INDEX
    Explanations

    server port configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    NAMESPACE
    -0.86
     polisi
    -0.81
    unez
    -0.75
     verheiratet
    -0.74
    只见
    -0.74
    Slate
    -0.74
    RNN
    -0.73
    inov
    -0.72
    Elections
    -0.71
    cpf
    -0.70
    POSITIVE LOGITS
     port
    0.96
    端口
    0.84
    urgy
    0.82
    Await
    0.82
    PORT
    0.82
    port
    0.79
    ⎧
    0.79
    setOnAction
    0.78
    ər
    0.77
     starten
    0.75
    Activations Density 0.027%

    No Known Activations