© 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. 67857
    Prev
    Next
    INDEX
    Explanations

    android layout attributes

    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
     rocher
    -1.48
     још
    -1.48
     francisco
    -1.48
     Signore
    -1.48
     nying
    -1.38
     ungefär
    -1.35
    álise
    -1.31
    kiej
    -1.30
    ятся
    -1.30
    墻
    -1.30
    POSITIVE LOGITS
     the
    1.80
     caráter
    1.41
     was
    1.38
     desenho
    1.38
     princípio
    1.38
     debería
    1.37
     ingresso
    1.36
     erhoben
    1.36
     direcciones
    1.36
     cenário
    1.34
    Activations Density 0.028%

    No Known Activations