© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129597
    Prev
    Next
    INDEX
    Explanations

    multilingual content identification

    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
     “
    -1.76
    ns
    -1.38
     "
    -1.31
    嵎
    -1.29
     rédu
    -1.29
    悒
    -1.27
     huwa
    -1.27
    ACTER
    -1.25
    ktionen
    -1.24
    ran
    -1.23
    POSITIVE LOGITS
    .
    1.58
     admiten
    1.46
    ambut
    1.41
    ménage
    1.41
     verschied
    1.40
     empezar
    1.35
    jadikan
    1.32
     recoger
    1.31
     esperan
    1.30
     oír
    1.30
    Activations Density 0.003%

    No Known Activations