© 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. 105007
    Prev
    Next
    INDEX
    Explanations

    all the more

    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
    呖
    -1.41
    PAIGN
    -1.39
     cualquiera
    -1.39
    喁
    -1.36
     masih
    -1.35
    廨
    -1.35
     énergie
    -1.34
     humorous
    -1.33
    laston
    -1.33
     taxe
    -1.30
    POSITIVE LOGITS
     they
    1.98
    各
    1.61
     each
    1.43
    每个
    1.37
    。
    1.34
    }\
    1.33
     после
    1.27
    ilyen
    1.23
     проєкту
    1.23
     only
    1.23
    Activations Density 0.004%

    No Known Activations