© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14364
    Prev
    Next
    INDEX
    Explanations

    end of sentence or phrase

    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
     pertandingan
    -1.03
     mainly
    -1.02
     on
    -1.00
     найбіль
    -0.98
     дуже
    -0.98
     mostly
    -0.93
    ！(
    -0.92
     краї
    -0.92
    jadikan
    -0.90
    katakan
    -0.88
    POSITIVE LOGITS
    both
    1.02
     😊
    1.01
    Its
    1.01
     Dinas
    1.00
     😁
    0.97
     lauded
    0.96
    Mvh
    0.93
    拄
    0.92
    也将
    0.90
    ヂ
    0.90
    Activations Density 0.058%

    No Known Activations