© 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. 22-GEMMASCOPE-RES-131K
    7. 13088
    Prev
    Next
    INDEX
    Explanations

    Java class declarations and constructors

    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
     nový
    -1.06
     megfelelő
    -1.05
    ῃ
    -0.98
     neuem
    -0.96
     szív
    -0.95
     技术
    -0.92
    детская
    -0.91
     pohod
    -0.88
    ˼
    -0.88
     rác
    -0.87
    POSITIVE LOGITS
     since
    0.87
    a
    0.86
    Ǧ
    0.84
     to
    0.82
     helping
    0.81
     pà
    0.81
    orted
    0.81
    ليز
    0.80
    ett
    0.80
     util
    0.79
    Activations Density 0.008%

    No Known Activations