© 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. 10-GEMMASCOPE-RES-131K
    7. 73963
    Prev
    Next
    INDEX
    Explanations

    court citations

    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_10/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
     litros
    -1.57
     they
    -1.50
    🌮
    -1.48
    ي
    -1.34
     respective
    -1.34
    شون
    -1.31
    timbangan
    -1.30
    ꯸
    -1.30
     Their
    -1.29
    щего
    -1.29
    POSITIVE LOGITS
     drawback
    2.00
    NOSIS
    1.91
     Notwendigkeit
    1.89
    the
    1.85
     Verpflichtung
    1.79
     diseñador
    1.77
     Eigentü
    1.74
     distinguishing
    1.73
     Trennung
    1.72
    Ѫ
    1.72
    Activations Density 0.056%

    No Known Activations