© 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. 10-GEMMASCOPE-RES-131K
    7. 43075
    Prev
    Next
    INDEX
    Explanations

    past versus nowadays

    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
    なんだろう
    -1.35
     alfombra
    -1.19
     orilla
    -1.18
     Kegiatan
    -1.15
    })$,
    -1.09
     diámetro
    -1.09
    quartile
    -1.09
    ướ
    -1.09
     encendido
    -1.08
     habitaciones
    -1.07
    POSITIVE LOGITS
     in
    1.43
     increasingly
    1.21
     asisten
    1.08
     voren
    1.05
    Venda
    1.05
    unikasi
    1.04
    After
    1.04
     После
    1.02
    太大
    1.02
     توسط
    1.01
    Activations Density 0.373%

    No Known Activations