© 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. 22-GEMMASCOPE-RES-131K
    7. 73449
    Prev
    Next
    INDEX
    Explanations

    multilingual text detection

    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_22/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
     two
    -1.17
     had
    -1.17
     also
    -1.13
     only
    -1.09
     time
    -1.08
     five
    -1.03
     first
    -1.03
     over
    -1.02
     this
    -1.02
     at
    -1.02
    POSITIVE LOGITS
     nimmer
    1.12
     côtes
    1.09
     milliers
    1.05
     biet
    1.04
    ceased
    1.04
    despite
    1.03
     SUCH
    1.02
     gefe
    1.02
     sérieux
    1.02
     verhind
    1.02
    Activations Density 0.076%

    No Known Activations