© 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. 10-GEMMASCOPE-RES-131K
    7. 119859
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     spion
    -1.03
     cif
    -0.98
    専用
    -0.93
     آزمون
    -0.92
    xos
    -0.91
     quarto
    -0.88
     bayan
    -0.88
     TOWN
    -0.88
    yden
    -0.88
     alber
    -0.85
    POSITIVE LOGITS
    gantian
    1.14
     cír
    1.13
    pulsera
    1.05
     inš
    1.05
     to
    1.04
     drifts
    1.02
    協議
    1.02
    jadikan
    1.02
     výro
    1.01
     inmediata
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.