© 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. 59746
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with fractions

    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
    -4.56
    2
    -4.16
    9
    -3.88
    3
    -3.75
    4
    -3.58
    5
    -3.38
    7
    -3.33
    6
    -3.17
    8
    -3.14
        
    -2.81
    POSITIVE LOGITS
     opérés
    2.67
    五日
    2.66
    
    2.58
    二百
    2.55
    ？』
    2.53
    するので
    2.45
    ：
    2.45
    
    2.44
    聾
    2.39
    あります
    2.38
    Activations Density 0.003%

    No Known Activations