© 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. 11172
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     work
    -0.88
     something
    -0.87
     our
    -0.87
     cũng
    -0.86
     some
    -0.85
     wadah
    -0.85
    玩的
    -0.85
     депута
    -0.84
     muchísimo
    -0.84
     دوباره
    -0.84
    POSITIVE LOGITS
     soie
    1.01
    ்
    0.94
    不锈钢
    0.94
    чия
    0.93
    itext
    0.91
    batt
    0.91
    quiv
    0.90
     seleccionados
    0.88
     jong
    0.88
    рена
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.