© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102782
    Prev
    Next
    INDEX
    Explanations

    section dividers

    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
    stoppable
    -1.43
    %;">
    -1.34
     elevados
    -1.33
     heilige
    -1.32
     dirigentes
    -1.31
     sabias
    -1.30
    )}+\
    -1.30
     Jahrhunderts
    -1.26
     }^{
    -1.25
    ありますが
    -1.24
    POSITIVE LOGITS
     that
    1.54
     maillot
    1.54
    For
    1.43
     pét
    1.34
     stuks
    1.34
     tijden
    1.33
     gebouwd
    1.28
     auquel
    1.27
    "-"
    1.27
     bebek
    1.26
    Activations Density 0.016%

    No Known Activations