© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48246
    Prev
    Next
    INDEX
    Explanations

    end all, help all, permanently destroy

    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
     jejich
    -1.45
    Inne
    -1.38
     їх
    -1.34
     they
    -1.32
     разных
    -1.31
     olika
    -1.27
     každý
    -1.25
     leur
    -1.23
    ícias
    -1.23
     mereka
    -1.23
    POSITIVE LOGITS
     its
    1.46
     how
    1.40
     stadt
    1.21
     with
    1.21
    果
    1.17
     then
    1.10
     ayrıca
    1.10
     նաև
    1.10
     Toxicological
    1.09
    such
    1.08
    Activations Density 0.174%

    No Known Activations