© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60041
    Prev
    Next
    INDEX
    Explanations

    python, PyObject, or Pennsylvania

    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
    Jetzt
    -0.76
    titur
    -0.75
    itoa
    -0.74
    Tray
    -0.73
     Appreciation
    -0.72
    Liefs
    -0.71
     powin
    -0.71
     администра
    -0.70
    enddo
    -0.70
    getline
    -0.69
    POSITIVE LOGITS
     Py
    1.69
    Py
    1.43
     pygame
    1.33
     PY
    1.31
    PyObject
    1.22
     Python
    1.20
     PYTHON
    1.19
    PY
    1.14
     Pennsylvania
    1.13
     python
    1.10
    Activations Density 0.017%

    No Known Activations