© 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. 8048
    Prev
    Next
    INDEX
    Explanations

    Go fmt package usage

    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
     encarga
    -2.58
    沄
    -2.55
    ᨅ
    -2.53
    激烈
    -2.38
     gdyż
    -2.38
     vieler
    -2.31
    obrázek
    -2.23
     nač
    -2.23
    輒
    -2.23
    ↵
    -2.22
    POSITIVE LOGITS
    镦
    2.73
    1
    2.39
    to
    2.34
     inoxydable
    2.28
    re
    2.25
    In
    2.19
    颪
    2.19
    >
    2.09
     вашу
    2.09
     appara
    2.09
    Activations Density 0.004%

    No Known Activations