© 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. 38792
    Prev
    Next
    INDEX
    Explanations

    European Spallation Source

    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
     препара
    -0.99
    per
    -0.89
    time
    -0.87
     per
    -0.85
     line
    -0.85
    dbf
    -0.84
    logError
    -0.82
    和你
    -0.82
     log
    -0.81
    Revista
    -0.79
    POSITIVE LOGITS
     Layanan
    0.98
     Lagi
    0.95
     these
    0.94
     kurikulum
    0.93
    绉
    0.92
     усі
    0.92
    liſh
    0.88
    <0xA3>
    0.87
     proposte
    0.87
    ᾴ
    0.86
    Activations Density 0.000%

    No Known Activations