© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6806
    Prev
    Next
    INDEX
    Explanations

    prefix "Fe"

    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
    
    -0.82
    ㅇ
    -0.80
     буль
    -0.79
     Dara
    -0.78
     monumento
    -0.77
     THEOREM
    -0.77
    ATA
    -0.76
     Haram
    -0.75
     mechanics
    -0.75
    पु
    -0.74
    POSITIVE LOGITS
     Fe
    1.91
    Fe
    1.80
     fe
    1.80
     FE
    1.47
     Фе
    1.30
    fe
    1.19
    FE
    1.15
     фе
    1.14
     Fey
    1.10
     Fé
    1.08
    Activations Density 0.055%

    No Known Activations