© 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. 116797
    Prev
    Next
    INDEX
    Explanations

    covered in

    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
    ここで
    -0.95
     enthalten
    -0.94
    db
    -0.93
     energías
    -0.91
     diámetro
    -0.90
     vegetación
    -0.90
    上に
    -0.89
     على
    -0.89
     accidentes
    -0.88
    jimo
    -0.87
    POSITIVE LOGITS
     in
    4.56
     dalam
    1.52
     في
    1.13
     with
    1.11
     în
    1.08
     във
    1.08
     در
    1.02
    іан
    0.98
     میں
    0.97
    માં
    0.94
    Activations Density 0.026%

    No Known Activations