Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8406
    Prev
    Next
    INDEX
    Explanations

    android layout orientation

    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_34/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
     aplicação
    -0.81
     للإ
    -0.77
     Multiplayer
    -0.75
     accompagner
    -0.73
    actéristique
    -0.73
    setHeight
    -0.73
     informações
    -0.73
     cambios
    -0.72
    eczki
    -0.72
     กล่อง
    -0.72
    POSITIVE LOGITS
    addView
    1.52
     orientation
    1.44
     Orientation
    1.38
    orientation
    1.35
    Orientation
    1.29
     orientations
    0.96
    removeAll
    0.95
     orient
    0.95
    weight
    0.91
     weight
    0.91
    Activations Density 0.027%

    No Known Activations