© 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. 118289
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    defined
    -0.90
     Explained
    -0.82
    Defined
    -0.82
     definiert
    -0.80
    angan
    -0.78
     medizin
    -0.77
     Defined
    -0.76
    ೈ
    -0.75
     UserDetails
    -0.75
    ounted
    -0.75
    POSITIVE LOGITS
     written
    1.51
     formas
    1.28
     rewritten
    1.26
    的形式
    1.23
     forms
    1.23
     bentuk
    1.19
     escrita
    1.08
    Forms
    1.05
    written
    1.05
     compact
    1.04
    Activations Density 0.036%

    No Known Activations