© 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. 69309
    Prev
    Next
    INDEX
    Explanations

    his idea

    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
     také
    -1.52
     mexicanos
    -1.48
    ógicos
    -1.47
     Detta
    -1.34
    ал
    -1.33
     também
    -1.33
    忡
    -1.33
    {~
    -1.32
     большин
    -1.32
     международ
    -1.31
    POSITIVE LOGITS
     or
    2.00
    \
    1.58
    ichtete
    1.57
     if
    1.52
     she
    1.51
     آفتاب
    1.47
    申し上げます
    1.42
     acoper
    1.40
    Étymologie
    1.39
     interieur
    1.36
    Activations Density 0.025%

    No Known Activations