© 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. 120050
    Prev
    Next
    INDEX
    Explanations

    invoking specific actions or entities

    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
    {
    -3.50
    </h3>
    -3.11
    )
    -2.77
    A
    -2.75
    </u>
    -2.47
    ."
    -2.38
    </strong>
    -2.34
    ",
    -2.28
    ":
    -2.23
    as
    -2.14
    POSITIVE LOGITS
    เพราะ
    2.39
     Для
    2.25
     kullanılan
    2.13
    増えて
    2.13
     kteří
    2.13
     vektör
    2.09
     Эти
    2.08
     frecuentemente
    2.06
     but
    2.05
     Этот
    2.05
    Activations Density 0.005%

    No Known Activations