© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38777
    Prev
    Next
    INDEX
    Explanations

    live events performances

    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
    3
    -1.39
    S
    -1.23
     thậm
    -1.13
    st
    -1.09
     are
    -1.09
     have
    -1.08
    名叫
    -1.08
     
    -1.08
    L
    -1.06
     colliding
    -1.05
    POSITIVE LOGITS
     sukienka
    1.41
    樣子
    1.28
    '))
    1.23
     ještě
    1.23
    .")
    1.18
    ጳ
    1.17
    vedať
    1.16
    ︠
    1.16
     chaqueta
    1.16
     продукти
    1.16
    Activations Density 0.042%

    No Known Activations