© 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. 10-GEMMASCOPE-RES-131K
    7. 61346
    Prev
    Next
    INDEX
    Explanations

    technical and multilingual contexts

    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_10/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
    Then
    -1.34
    When
    -1.27
    Only
    -1.26
    𝐱
    -1.26
    when
    -1.23
    нівер
    -1.23
     then
    -1.22
     ONLY
    -1.21
     only
    -1.20
     лишь
    -1.17
    POSITIVE LOGITS
     they
    1.23
     slike
    1.13
     would
    1.13
     vitesses
    1.13
     cellulare
    1.12
     garantir
    1.09
    רא
    1.09
     orologio
    1.09
     ステン
    1.08
     wszystkie
    1.07
    Activations Density 0.479%

    No Known Activations