© 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. 129466
    Prev
    Next
    INDEX
    Explanations

    following to

    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
     mientras
    -1.48
     زیرا
    -1.32
     zarówno
    -1.28
     потому
    -1.27
     یک
    -1.26
     após
    -1.24
     porque
    -1.24
     nachdem
    -1.23
    %;
    -1.23
     یکی
    -1.21
    POSITIVE LOGITS
     groet
    1.30
    端的
    1.24
    denk
    1.23
    tický
    1.21
     themselves
    1.16
     nuvem
    1.14
     skak
    1.13
     gruppen
    1.13
     all
    1.13
     hvil
    1.13
    Activations Density 0.186%

    No Known Activations