© 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. 44864
    Prev
    Next
    INDEX
    Explanations

    sensor input and data

    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
    y
    -2.78
     или
    -2.64
    your
    -2.50
     یا
    -2.50
     icône
    -2.44
    ?"
    -2.36
    ی
    -2.31
    out
    -2.30
     payé
    -2.30
    os
    -2.23
    POSITIVE LOGITS
    屃
    2.52
    狆
    2.42
    骝
    2.31
    椏
    2.28
     冷凍
    2.27
     fresca
    2.22
    岜
    2.22
    
    2.20
    ające
    2.17
    ⚌
    2.17
    Activations Density 0.009%

    No Known Activations