© 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. 8815
    Prev
    Next
    INDEX
    Explanations

    PO Box and postal addresses

    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
     suave
    -1.31
     ultime
    -1.27
    嗒
    -1.26
     -
    -1.24
    upon
    -1.23
     teneb
    -1.23
     confr
    -1.20
     affaires
    -1.17
    ائومی
    -1.17
    they
    -1.16
    POSITIVE LOGITS
     which
    1.48
     elástico
    1.44
     zowel
    1.38
     necesarios
    1.34
     both
    1.27
     innym
    1.20
     ajustado
    1.20
    年は
    1.19
    軀
    1.18
     separado
    1.16
    Activations Density 0.018%

    No Known Activations