© 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. 22-GEMMASCOPE-RES-131K
    7. 130253
    Prev
    Next
    INDEX
    Explanations

    Python code, especially file paths

    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_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
     Jimenez
    -0.98
    змом
    -0.98
     Jiménez
    -0.94
    æs
    -0.94
    না
    -0.88
    IElement
    -0.88
     žiad
    -0.87
    setCellValue
    -0.86
    :'',
    -0.85
     Wissenschaft
    -0.85
    POSITIVE LOGITS
     duelo
    0.77
     sólidos
    0.77
    CHORUS
    0.77
    を開始
    0.76
    gesetz
    0.76
     `${
    0.73
    しましたが
    0.72
    folgung
    0.72
    落下
    0.71
    extract
    0.71
    Activations Density 0.005%

    No Known Activations