© 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. 10-GEMMASCOPE-RES-131K
    7. 210
    Prev
    Next
    INDEX
    Explanations

    if you are using

    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
     aar
    -1.38
     gita
    -1.34
     pey
    -1.30
     erin
    -1.28
     mann
    -1.28
     hama
    -1.28
     oll
    -1.27
     eur
    -1.27
     hansen
    -1.25
     silva
    -1.24
    POSITIVE LOGITS
     your
    1.66
    }>;
    1.55
     Those
    1.54
     this
    1.50
     neuen
    1.50
     duelo
    1.38
    .}(
    1.38
     unterstützen
    1.36
     erlä
    1.36
     for
    1.34
    Activations Density 0.144%

    No Known Activations