© 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. 32989
    Prev
    Next
    INDEX
    Explanations

    names starting with Fab

    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
     भ
    -0.75
    蕨
    -0.75
    Stim
    -0.75
    下单
    -0.74
     mela
    -0.73
     stimul
    -0.73
     nele
    -0.72
     gagal
    -0.70
     Lä
    -0.70
    %%%
    -0.70
    POSITIVE LOGITS
     Faber
    0.96
     Fab
    0.90
     easterly
    0.90
    Fab
    0.89
     asegurar
    0.81
    Fourni
    0.80
    ardı
    0.77
     incorporación
    0.76
    WAH
    0.76
     fab
    0.75
    Activations Density 0.017%

    No Known Activations