© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67393
    Prev
    Next
    INDEX
    Explanations

    ggplot and plotting

    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
    骉
    -1.84
    Sebelumnya
    -1.62
    Bahkan
    -1.60
    毳
    -1.57
     cidades
    -1.57
     colazione
    -1.56
    锖
    -1.56
    憷
    -1.55
    ᾗ
    -1.54
    蕷
    -1.53
    POSITIVE LOGITS
    {
    1.84
    </h3>
    1.63
     
    1.60
     \
    1.45
     We
    1.42
    viembre
    1.37
     Unlike
    1.35
    autogui
    1.32
     que
    1.31
     sensible
    1.28
    Activations Density 0.004%

    No Known Activations