© 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. 74018
    Prev
    Next
    INDEX
    Explanations

    as long as

    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
     atacado
    -1.59
    大学の
    -1.57
     also
    -1.49
    </sup>
    -1.48
     protože
    -1.47
    ㍑
    -1.44
    </h4>
    -1.42
     domésticos
    -1.41
     específica
    -1.41
     revelado
    -1.41
    POSITIVE LOGITS
    You
    1.38
    PointerException
    1.36
     adage
    1.35
     ми
    1.30
    ↵
    1.29
    Any
    1.28
    Folgende
    1.28
     {
    1.27
     iLocal
    1.26
    ࿆
    1.26
    Activations Density 0.003%

    No Known Activations