© 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. 69911
    Prev
    Next
    INDEX
    Explanations

    Android UI layouts and finding elements

    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
     was
    -2.81
     seems
    -2.73
     has
    -2.44
     "
    -2.38
     does
    -2.31
     took
    -2.27
     is
    -2.23
     gives
    -2.23
     came
    -2.23
     had
    -2.22
    POSITIVE LOGITS
     utiliser
    2.73
     appliquer
    2.20
     türkiye
    2.16
     envoyer
    2.14
     enlever
    2.13
     iNdEx
    2.09
     ajouter
    2.09
    缛
    2.05
    ❁
    2.05
     appeler
    2.05
    Activations Density 0.025%

    No Known Activations