© 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. 47929
    Prev
    Next
    INDEX
    Explanations

    what is expanded

    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
     The
    -2.70
    {
    -2.56
    秾
    -2.13
    乖乖
    -2.08
    廰
    -2.05
     começ
    -2.02
    都想
    -1.99
    好好的
    -1.98
    にい
    -1.97
     daring
    -1.95
    POSITIVE LOGITS
    姈
    2.61
     expanded
    2.56
    之前的
    2.52
    ～。
    2.48
    asiswa
    2.45
    問題は
    2.41
    。『
    2.39
    an
    2.34
    Not
    2.33
    नलोड
    2.33
    Activations Density 0.003%

    No Known Activations