© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28335
    Prev
    Next
    INDEX
    Explanations

    multi-lingual comparisons

    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
     februar
    -1.20
    kologie
    -1.11
    dungen
    -1.09
     krep
    -1.08
    esity
    -1.07
    ونية
    -1.05
    häuse
    -1.02
    landı
    -0.98
     jugos
    -0.98
    각주
    -0.97
    POSITIVE LOGITS
     betrachten
    1.04
     ısı
    0.97
    也可以
    0.96
    •
    0.96
     deose
    0.94
    ても
    0.93
    跟着
    0.91
    优秀
    0.91
     ろう
    0.90
    すば
    0.90
    Activations Density 0.001%

    No Known Activations