© 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. 67447
    Prev
    Next
    INDEX
    Explanations

    forms of "to be"

    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
    廡
    -1.34
     surpren
    -1.34
    FAMIL
    -1.27
    stücks
    -1.23
    这也
    -1.21
     behöver
    -1.21
    мира
    -1.20
    餒
    -1.17
     für
    -1.16
    ͎
    -1.16
    POSITIVE LOGITS
     this
    1.31
     when
    1.30
    quirer
    1.27
     helicópter
    1.27
    during
    1.23
    magine
    1.23
     spół
    1.20
    🙂
    1.16
     at
    1.16
     μας
    1.14
    Activations Density 0.011%

    No Known Activations