© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73865
    Prev
    Next
    INDEX
    Explanations

    closing code comments

    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
     bringing
    -0.91
    <eos>
    -0.90
     its
    -0.90
     brings
    -0.88
     getting
    -0.86
     making
    -0.84
     before
    -0.84
     because
    -0.82
     gets
    -0.81
     with
    -0.79
    POSITIVE LOGITS
    */
    
    1.16
    **/
    1.14
    */
    1.06
     **/
    1.04
    <h4>
    1.04
    *\
    0.96
    */}
    0.93
    albeit
    0.93
    
    0.91
    ̅
    0.85
    Activations Density 0.042%

    No Known Activations