© 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. 65242
    Prev
    Next
    INDEX
    Explanations

    Q: package Filed

    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
     dengan
    -1.67
    Они
    -1.52
    чну
    -1.51
    🏢
    -1.50
     diagrama
    -1.48
    疍
    -1.46
     ними
    -1.41
     sehr
    -1.41
    ⬮
    -1.38
    🫣
    -1.38
    POSITIVE LOGITS
     we
    1.84
     takiego
    1.63
     then
    1.46
     not
    1.46
    そういう
    1.45
     takim
    1.43
     walaupun
    1.41
    られていた
    1.41
    られている
    1.39
    菒
    1.38
    Activations Density 0.000%

    No Known Activations