© 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. 58921
    Prev
    Next
    INDEX
    Explanations

    specific details and facts

    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
    Nazwa
    -1.07
    糹
    -0.99
    This
    -0.96
    gibt
    -0.94
    gruß
    -0.94
    Gründe
    -0.92
    ஏ
    -0.92
    anniversary
    -0.90
    VIATIONS
    -0.89
    ஊ
    -0.89
    POSITIVE LOGITS
    :
    1.38
     Ã
    1.31
     also
    1.25
            
    1.24
              
    1.23
    および
    1.23
    そして
    1.18
    Ã
    1.18
                
    1.18
        
    1.18
    Activations Density 30.460%

    No Known Activations