© 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. 70134
    Prev
    Next
    INDEX
    Explanations

    UI element declarations

    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
    onBlur
    -0.85
     actionPerformed
    -0.84
     innumerable
    -0.83
     {
    -0.82
     ALWAYS
    -0.79
     there
    -0.77
     its
    -0.77
     IconData
    -0.77
    formKey
    -0.77
    <tr>
    -0.77
    POSITIVE LOGITS
    findViewById
    1.57
     view
    1.09
    Compat
    1.01
     Kotlin
    1.00
     findViewById
    0.99
    =(
    0.98
    ="@+
    0.94
    tv
    0.94
     toolbar
    0.94
     recy
    0.92
    Activations Density 0.009%

    No Known Activations