© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101716
    Prev
    Next
    INDEX
    Explanations

    control, support, objectives, empowerment

    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
     only
    -1.74
    氏
    -1.38
    只有
    -1.31
    ...
    -1.30
     apesar
    -1.27
    其
    -1.27
    8
    -1.24
     السياسي
    -1.23
    only
    -1.21
    幾
    -1.20
    POSITIVE LOGITS
    してた
    1.62
    tentu
    1.59
     pás
    1.34
    1.34
    </>
    1.34
     discursos
    1.34
    ⣟
    1.29
     tady
    1.28
     ४
    1.28
     gimnas
    1.27
    Activations Density 0.022%

    No Known Activations