© 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. 76078
    Prev
    Next
    INDEX
    Explanations

    graduated with Bachelor of degrees

    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
    Doctoral
    -0.81
    UD
    -0.81
    潮
    -0.80
    ULE
    -0.74
     Jaya
    -0.72
     مرة
    -0.71
    Cf
    -0.70
    
    -0.70
    ు
    -0.69
    STRO
    -0.68
    POSITIVE LOGITS
     commerce
    1.05
     Commerce
    1.04
    articles
    0.75
     double
    0.75
     honra
    0.73
     chuyên
    0.70
    נח
    0.70
     gereken
    0.69
    自治
    0.69
    )=\
    0.68
    Activations Density 0.030%

    No Known Activations