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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72437
    Prev
    Next
    INDEX
    Explanations

    HTML table structures

    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_10/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
        
    -1.65
     Faktoren
    -1.53
    );
    -1.52
     receive
    -1.52
          
    -1.51
    These
    -1.49
            
    -1.49
                             
    -1.48
     be
    -1.45
    我们的
    -1.41
    POSITIVE LOGITS
     that
    1.97
    힛
    1.79
    aning
    1.77
    嵛
    1.66
     másik
    1.59
     annan
    1.56
    雱
    1.56
    几个人
    1.54
    albeit
    1.50
    蘚
    1.50
    Activations Density 0.004%

    No Known Activations