© 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. 58869
    Prev
    Next
    INDEX
    Explanations

    android xml namespaces

    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
     there
    -0.87
    株式
    -0.85
    oudoune
    -0.81
     gruesa
    -0.79
     ^{\
    -0.79
    tados
    -0.78
    想着
    -0.77
    стройство
    -0.77
    名为
    -0.76
    ところに
    -0.76
    POSITIVE LOGITS
    _
    1.11
     cipolla
    1.08
     uova
    1.04
     –
    1.02
    的人
    1.00
    Библи
    1.00
    <bos>
    0.98
    __
    0.96
    — 
    0.94
    ___
    0.93
    Activations Density 0.001%

    No Known Activations