© 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. 6702
    Prev
    Next
    INDEX
    Explanations

    international economic and cultural convergence

    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
    たって
    -1.34
     by
    -1.34
    ・・。
    -1.16
    と感じ
    -1.16
     to
    -1.15
     in
    -1.15
    ですが
    -1.11
    年は
    -1.09
    但这
    -1.07
     impecable
    -1.07
    POSITIVE LOGITS
    に入れて
    1.51
    に入れる
    1.38
    様な
    1.32
    に入れ
    1.29
     gemeenten
    1.20
     musia
    1.16
     cerâmica
    1.14
     ozdob
    1.11
    ところに
    1.10
     estacionamento
    1.10
    Activations Density 0.004%

    No Known Activations