© 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. 21985
    Prev
    Next
    INDEX
    Explanations

    binary digits or computing bits

    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
    灕
    -3.08
    
    -2.47
     estadía
    -2.39
    vantaged
    -2.33
    庒
    -2.30
    鷓
    -2.27
     самых
    -2.27
    ⤒
    -2.20
    
    -2.20
     disposición
    -2.17
    POSITIVE LOGITS
    饪
    3.11
    觧
    2.77
     необходимо
    2.77
    section
    2.64
    </strong>
    2.56
    лению
    2.45
     consider
    2.39
    汌
    2.39
    s
    2.39
    та
    2.38
    Activations Density 0.002%

    No Known Activations