© 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. 101584
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    -2.77
        
    -2.41
           
    -2.16
       
    -2.11
    3
    -2.02
         
    -2.00
     still
    -1.95
     usually
    -1.93
     they
    -1.91
    2
    -1.86
    POSITIVE LOGITS
    </em>
    2.19
    
    2.19
     авгу
    2.16
    iiii
    2.06
    口气
    2.05
    </i>
    2.05
     zoude
    1.99
     OGSÅ
    1.93
    ཥ
    1.91
    鼕
    1.90
    Activations Density 0.008%

    No Known Activations