© 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. 113624
    Prev
    Next
    INDEX
    Explanations

    Android UI elements

    np_acts-logits-general · gemini-2.5-flash-lite

    references to Android layout resource identifiers in code, particularly `R.layout` followed by a resource name.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     maravillosas
    -1.56
     réputation
    -1.51
    étiques
    -1.46
     suspensão
    -1.45
    汌
    -1.39
     who
    -1.37
     sugary
    -1.35
    zeera
    -1.35
    Oneof
    -1.34
     mismas
    -1.33
    POSITIVE LOGITS
     for
    1.66
    梣
    1.45
     of
    1.45
     שלהם
    1.38
    a
    1.38
     Sociale
    1.37
    呖
    1.36
     素描
    1.33
     after
    1.30
     для
    1.30
    Activations Density 0.009%

    No Known Activations