© 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. 19844
    Prev
    Next
    INDEX
    Explanations

    preparation or preparing something

    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
    𓋼
    -2.63
    \_
    -2.23
     esche
    -2.20
    V
    -2.17
     pérd
    -2.09
     $^{\
    -2.09
    B
    -2.08
    </h2>
    -2.05
    2
    -2.05
    一九
    -2.02
    POSITIVE LOGITS
     If
    2.22
    riezmann
    2.06
    凊
    1.96
     Luckily
    1.92
     Undoubtedly
    1.89
     According
    1.88
    壽司
    1.88
    </u>
    1.85
     Fortunately
    1.81
     Specifically
    1.79
    Activations Density 0.027%

    No Known Activations