© 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. 92550
    Prev
    Next
    INDEX
    Explanations

    complex roots

    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
     بور
    -0.86
    ienza
    -0.74
    Samstag
    -0.73
    throm
    -0.71
     McConnell
    -0.71
     doté
    -0.70
    song
    -0.69
    Analysts
    -0.68
     Sutton
    -0.68
    γραφή
    -0.68
    POSITIVE LOGITS
     primitive
    1.29
    primitive
    1.18
     roots
    1.16
    omega
    0.96
     root
    0.96
     ω
    0.95
     Roots
    0.93
     Primitive
    0.91
     omega
    0.88
    Primitive
    0.87
    Activations Density 0.061%

    No Known Activations