© 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. 84104
    Prev
    Next
    INDEX
    Explanations

    general scope or summary

    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
     as
    -1.89
     for
    -1.68
     while
    -1.66
     or
    -1.61
     at
    -1.59
     before
    -1.59
     alongside
    -1.57
     without
    -1.56
    </u>
    -1.55
     such
    -1.55
    POSITIVE LOGITS
     laiss
    1.75
     mauva
    1.68
     wszystkich
    1.66
     saludables
    1.62
     refroid
    1.60
     bascul
    1.56
     тебя
    1.55
    ᗷ
    1.55
     noirs
    1.55
     bleus
    1.51
    Activations Density 0.003%

    No Known Activations