© 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. 47940
    Prev
    Next
    INDEX
    Explanations

    Expression Operator

    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
     inmun
    -1.63
     欣赏
    -1.54
    靣
    -1.51
     процесса
    -1.50
     facilita
    -1.49
     garan
    -1.45
    ;<
    -1.45
     carcasa
    -1.44
     durch
    -1.43
     喝
    -1.41
    POSITIVE LOGITS
    1
    1.81
    9
    1.72
    4
    1.66
    ämään
    1.47
     he
    1.46
    oquia
    1.40
    3
    1.38
     of
    1.38
    лению
    1.36
     nowych
    1.32
    Activations Density 0.000%

    No Known Activations