© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117970
    Prev
    Next
    INDEX
    Explanations

    Android UI inflation

    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
     /*#__
    -0.85
     UIImageView
    -0.84
     getIntent
    -0.83
     Japão
    -0.81
    ğını
    -0.80
    )))),
    -0.79
    BaseActivity
    -0.78
     arī
    -0.78
     clássico
    -0.77
    DOWN
    -0.77
    POSITIVE LOGITS
     Inflate
    1.43
     inflate
    1.06
     inflated
    1.06
     inflation
    1.05
     INFL
    1.04
    setHas
    1.02
    Infl
    0.98
     onCreateView
    0.95
     inflater
    0.95
    inflater
    0.93
    Activations Density 0.008%

    No Known Activations