© 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. 118931
    Prev
    Next
    INDEX
    Explanations

    a little bit

    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
    0
    -1.72
     =
    -1.57
    ↵↵↵↵
    -1.51
     “
    -1.35
     लेकिन
    -1.32
     क्योंकि
    -1.29
    겟
    -1.28
     而
    -1.25
     that
    -1.23
    D
    -1.21
    POSITIVE LOGITS
    </strong>
    1.62
     brilh
    1.56
    ſu
    1.56
    ities
    1.55
    いかがでしたか
    1.53
     OBITUARY
    1.53
    \|^{
    1.47
    叭
    1.46
    推荐阅读
    1.45
     bordado
    1.45
    Activations Density 0.235%

    No Known Activations