© 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. 381
    Prev
    Next
    INDEX
    Explanations

    xhtml doctype or links

    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
     for
    -1.73
    ૉ
    -1.34
     soltanto
    -1.32
     voelen
    -1.28
    だけです
    -1.27
     officielles
    -1.24
     exhibición
    -1.24
     adatto
    -1.22
     it
    -1.19
     красный
    -1.19
    POSITIVE LOGITS
    izate
    1.57
     Dentro
    1.57
    itizing
    1.52
     personnage
    1.52
    isait
    1.51
    ΄
    1.47
     lojas
    1.45
    ouncement
    1.45
    pinMode
    1.43
    {§
    1.38
    Activations Density 0.005%

    No Known Activations