© 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. 4316
    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_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
     assumed
    -0.83
    collating
    -0.80
     冊
    -0.79
    ならず
    -0.79
     Staates
    -0.79
     such
    -0.79
     pagkak
    -0.79
    という言葉
    -0.77
     suspected
    -0.77
    鎳
    -0.77
    POSITIVE LOGITS
     gravity
    1.08
    weight
    1.07
    gravity
    1.06
    width
    0.89
    margin
    0.83
     margin
    0.81
    _
    0.80
     weight
    0.79
    Lo
    0.79
     sexuality
    0.78
    Activations Density 0.007%

    No Known Activations