© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13765
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and defines

    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
    that
    -2.72
    up
    -2.53
    when
    -2.50
    there
    -2.45
    Usually
    -2.44
    Shortly
    -2.33
     There
    -2.31
    </h2>
    -2.31
    我们在
    -2.31
    viembre
    -2.23
    POSITIVE LOGITS
    ☫
    3.36
    0
    2.66
    蕖
    2.42
    \]
    2.36
    渃
    2.34
     et
    2.28
    を購入
    2.25
     её
    2.23
    ⸎
    2.20
     complemented
    2.17
    Activations Density 0.185%

    No Known Activations