© 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. 22-GEMMASCOPE-RES-131K
    7. 25438
    Prev
    Next
    INDEX
    Explanations

    electronic devices and applications

    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_22/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
     туры
    -1.42
    atized
    -1.42
     hongos
    -1.41
    ೩
    -1.39
     triom
    -1.36
     offert
    -1.34
    кономи
    -1.34
    
    -1.34
     dát
    -1.32
    matory
    -1.30
    POSITIVE LOGITS
     with
    1.77
     after
    1.63
     and
    1.55
     related
    1.52
     that
    1.52
     support
    1.46
    𝑍
    1.37
     management
    1.34
     in
    1.34
     during
    1.31
    Activations Density 0.362%

    No Known Activations