© 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. 100089
    Prev
    Next
    INDEX
    Explanations

    long, longer, longest

    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
    {
    -2.05
    ㌘
    -1.70
     Там
    -1.59
     轉
    -1.59
     Rumuni
    -1.55
    bno
    -1.54
     There
    -1.51
     sogen
    -1.48
    StreetMap
    -1.48
     kini
    -1.47
    POSITIVE LOGITS
    length
    1.95
    \_
    1.73
     dài
    1.72
    3
    1.72
    ());
    1.70
    1
    1.70
     embl
    1.68
     length
    1.66
    長い
    1.66
     você
    1.65
    Activations Density 0.120%

    No Known Activations