© 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. 102716
    Prev
    Next
    INDEX
    Explanations

    m followed by numbers or scientific identifiers

    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
     by
    -1.40
     two
    -1.20
    Maybe
    -1.18
     '>=
    -1.16
     隊
    -1.16
    ياه
    -1.14
     five
    -1.13
     you
    -1.11
    oltán
    -1.10
     three
    -1.09
    POSITIVE LOGITS
     attirer
    1.36
    分かる
    1.32
     accompagner
    1.24
     diriger
    1.22
     Kindes
    1.21
     Besonder
    1.19
     geladeira
    1.19
    rehensible
    1.19
     känna
    1.16
     paroi
    1.16
    Activations Density 0.176%

    No Known Activations