© 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. 41284
    Prev
    Next
    INDEX
    Explanations

    new and distinct qualities

    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
     on
    -1.97
     for
    -1.61
     her
    -1.48
     vuelven
    -1.38
     using
    -1.34
     Arhivirano
    -1.29
     corriendo
    -1.27
     bailando
    -1.26
     posando
    -1.25
    </h1>
    -1.23
    POSITIVE LOGITS
     लेकिन
    1.57
    resizingMask
    1.50
     ſtre
    1.44
    vertebrates
    1.38
    ︐
    1.37
    said
    1.32
    を試
    1.32
    臯
    1.31
     dermed
    1.31
    cisive
    1.31
    Activations Density 0.051%

    No Known Activations