© 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. 22-GEMMASCOPE-RES-131K
    7. 34256
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     rigorously
    -1.19
     accidentally
    -1.13
     even
    -1.13
     secretly
    -1.13
     routinely
    -1.12
     allegedly
    -1.11
     whereas
    -1.10
     of
    -1.10
     subtly
    -1.10
     technically
    -1.09
    POSITIVE LOGITS
     Lokasi
    1.15
    ቪ
    1.09
    ほんとに
    1.03
    刪除
    0.98
     Lebih
    0.98
    maksi
    0.97
    添付
    0.97
     Dengan
    0.97
     camaraderie
    0.96
    阵法
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.