© 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. 67519
    Prev
    Next
    INDEX
    Explanations

    assignments involving numbers

    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
     we
    -1.20
     tomaron
    -1.12
     bây
    -1.12
     testigos
    -1.10
     livid
    -1.08
    Tyran
    -1.07
     escalier
    -1.06
     pères
    -1.05
     the
    -1.03
    ombie
    -1.03
    POSITIVE LOGITS
    ……」
    1.65
     two
    1.55
    …」
    1.45
    Some
    1.43
     dalamnya
    1.43
    </h1>
    1.41
     my
    1.30
     to
    1.30
     one
    1.27
     people
    1.27
    Activations Density 0.068%

    No Known Activations